We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in $n$-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT). Each task ships a CPU reference, a roofline-anchored fitness function, and a held-out generalization size. We pair the benchmark with a lightweight harness for automatic kernel search that runtime-compiles each candidate, scores it against the roofline across multiple sizes, and feeds structured compile and per-size correctness diagnostics back to a frozen LLM driving a $(1{+}1)$ evolutionary loop. We report matched single-model sweeps of Claude Opus 4.7, Gemini 3.1 Pro, and GPT 5.5 on M1 Pro: in-distribution self-speedups span $1.00\times$ to $10.7\times$. Beyond raw speedup, our central methodological claim is structural: the held-out gate scoring function $Φ_\mathcal{T}$ (evaluated once at end-of-run on a configuration the agent never sees during search) functions as a cheap mechanical oversight primitive on this automatic search loop, catching e.g. an Opus template <uint D> HMC win that returns wrong samples at unseen dimensions, and a GPT FFT3D best that wins in-distribution at $2.95\times$ speedup but collapses to $0.23\times$ on a $256^3$ held-out cube, a silent regression that the in-distribution score alone cannot see. Code at https://github.com/vicgalle/metal-sci-kernels

Training neural networks to satisfy universal constraints over continuous domains poses unique challenges. Common examples include Lyapunov Neural Networks (Lyapunov NNs) and Physics-Informed Neural Networks (PINNs), where analytical solutions are generally either unavailable or overly restrictive. Sample-based methods are therefore commonly used to enforce these constraints, and the choice of samples has a substantial impact on convergence speed, stability, and solution quality. Most existing methods rely on fixed heuristics or handcrafted rules, and are suboptimal in practice. In this paper, we aim to improve upon them by learning, from data and experience, how to dynamically and iteratively adjust the samples in response to the model's evolving learning performance. Trained by reinforcement learning, the learned policy improves empirical constraint satisfaction on test problems while significantly improving efficiency. We validate the approach on both Lyapunov NNs and PINNs, and demonstrate its broader applicability to domains where adaptive input selection is essential for effective training.

Understanding human mental states from natural behavior is crucial for intelligent systems in the real world. However, most current research focuses on predicting isolated mental state labels, lacking structured annotations of complex interpersonal interactions. To support structured analysis, we introduce MOTOR-Bench, a carefully-designed benchmark with a real-world dataset MOTOR-dataset, containing 1,440 multimodal video clips in collaborative learning scenarios, reflecting key real-world data challenges including natural class imbalance, visual noise, and domain-specific language. Each sample is labeled by educational experts based on self-regulated learning theory. We further evaluate several state-of-the-art multimodal large language models and multi-agent systems in a zero-shot setting on our MOTOR-Bench. However, their performance on this task remains limited, suggesting that existing methods still struggle with structured reasoning from observable behavior to deeper mental states. To address this challenge, we propose a reasoning multi-agent framework, named MOTOR-MAS. It coordinates multiple agents through a structured agent coordination mechanism to infer explicit behaviors, internal cognitions, and psychological emotions. Experimental results show that our MOTOR-MAS outperforms the best single-model benchmark by 15.93 points in Macro-F1 scores for the three labels of behavior, cognition, and emotion, and outperforms the general multi-agent benchmark by 10.2 points in internal cognition prediction.

Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat future latent states as prediction targets or auxiliary signals, rather than directly conditioning trajectory planning. This can entangle current and future features in latent space. In this work, we propose DriveFuture, a future-aware latent world modeling framework for autonomous driving that explicitly learns planning-oriented foresight by conditioning the current latent state modeling process on future world states. Specifically, during training, the model first predicts future latent world states from the current latent state and ego action, and then refines the prediction against the ground-truth future latent state via cross-attention. The resulting future-aware latent serves as an explicit condition for a diffusion-based trajectory planner. During inference, DriveFuture conditions on the predicted future latent state instead of the ground-truth future state. DriveFuture achieves SOTA performance on the public NAVSIM benchmarks, reaching \textbf{55.5} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}, \textbf{89.9} EPDMS on NAVSIM-v2 {\textcolor{blue}{\textit{navtest}}}, and \textbf{90.7} PDMS on NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}, respectively. These results suggest that the key to latent world modeling lies not merely in simulating future states, but more importantly in conditioning current decision-making on future states. Notably, as of April 2026, DriveFuture ranks \textbf{1st} on the \href{https://huggingface.co/spaces/AGC2025/e2e-driving-navhard}{NAVSIM-v2 {\textcolor{blue}{\textit{navhard}}}} leaderboard and achieves SOTA performance on \href{https://huggingface.co/spaces/AGC2024-P/e2e-driving-navtest}{NAVSIM-v1 {\textcolor{blue}{\textit{navtest}}}}.

As data-science agents shift from co-pilots to auto-pilots, silent misframing becomes a critical failure mode. Agents quietly commit to plausible but unintended task framings, producing clean, executable artifacts that hide their incorrect assessment of the task. Existing benchmarks score whether the pipeline runs, ignoring whether the agent recognized the task was underspecified. We introduce Ambig-DS, two diagnostic suites: one for prediction-target ambiguity (Ambig-DS-Target, 51 tasks built on DSBench, a tabular modeling benchmark) and one for evaluation-objective ambiguity (Ambig-DS-Objective, 61 tasks built on MLE-bench, a Kaggle-style ML competition benchmark), constructed so that scoring uses each source benchmark's original evaluator. For every task we pair the original, fully specified version with an ambiguous variant produced by controlled edits; a human-and-LLM verification pipeline confirms each variant admits multiple plausible interpretations with decision-relevant consequences. The suites are analyzed independently and ambiguity lowers performance in both. Across five agents spanning efficient to frontier-class models, we find in our controlled diagnostic setting: (i) failures are silent commitments: wrong-target submissions on Target, wrong-metric or non-committal baseline submissions on Objective, rather than execution errors; (ii) allowing the agent to ask one clarifying question recovers much of the loss under idealized conditions, suggesting missing framing information drives a substantial part of the observed degradation; but (iii) agents cannot reliably tell when to use it: permissive prompts induce over-asking on clear tasks, while conservative prompts induce silent defaulting on ambiguous ones. Recognizing target and objective underspecification, not pipeline execution, is the bottleneck missing from standard DS-agent evaluations.

Discovering governing equations from observational data remains a fundamental challenge in scientific modeling, particularly when the underlying mathematical structure is unknown. Traditional sparse identification methods like SINDy excel at discovering parsimonious models but require researchers to specify candidate basis functions a priori, a limitation that often leads to model failure when critical terms are omitted or when systems exhibit unconventional dynamics. Purely symbolic regression approaches offer unlimited flexibility but struggle with noise sensitivity and frequently produce overly complex, unstable equations. We present AutoSINDy, a hybrid Discovery-then-Solve framework that combines the exploratory power of symbolic regression with the robust sparsity-promoting capabilities of SINDy. Our method operates in three stages: (1) PySR-based symbolic regression discovers candidate functional forms from bootstrapped data chunks; (2) a curation pipeline decomposes, expands, and filters these expressions using collinearity analysis to construct a minimal yet comprehensive library; and (3) SINDy identifies sparse governing equations from this custom-tailored library. Extensive experiments across canonical nonlinear systems demonstrate that AutoSINDy consistently recovers ground-truth equations even under high observational noise, achieving a ground-truth recovery rate of 92.8% across all trials. Compared with standard SINDy using enriched libraries and standalone symbolic regression, AutoSINDy achieves higher predictive accuracy, superior generalization to unseen trajectories, and substantially lower symbolic complexity.

Yes. We find that large multimodal models develop mental imagery when solving spatial puzzles, and they do imagine sheep when solving sheep puzzles. We fine-tune a Qwen3.5 VLM to solve twelve diverse visual reasoning tasks -- including tangram, jigsaw, sokoban, 3D mental rotation, and rush hour -- that require understanding geometry, spatial relationships, and the consequences of actions. By supervising the model to predict the open-loop sequence of actions to solve a puzzle from an initial state, we show that the model's activations after each action encode meaningful visual information about the intermediate state. This finding suggests that an imperfect visual world model begins to form as a byproduct of learning to select correct actions, in the absence of any explicit visual supervision. Building on this observation, we propose two ways to sharpen and use the mental images formed by the model. We find that integrating as few as sixteen visual tokens per step into the chain of thought improves the average solve rate from 83% to 89%, with particularly strong gains on reasoning-heavy tasks such as jigsaw and 3D mental rotation.

Population pharmacokinetic/pharmacodynamic (PK/PD) modeling traditionally relies on classical ordinary differential equations to simulate drug dynamics. In this work, we reformulate a compartmental PK/PD model as an open quantum system and implement it using quantum circuits developed in PennyLane. Four pharmacological compartments (central, peripheral, effect-site, and response) are encoded using twelve qubits, with inter-compartmental transitions represented through controlled quantum operations that emulate stochastic dynamics. The framework is evaluated on Phase 1 clinical data using a quantum-enhanced stochastic approximation expectation-maximization (SAEM) approach. Compared with the classical implementation, the quantum model achieves substantially improved log-likelihood values, indicating stronger statistical fit while preserving identical parameter estimates, thereby validating numerical consistency and model interpretability. The quantum-based optimization converges faster in terms of iterations, although total runtime is increased due to current simulation overhead. The study demonstrates stable large-scale simulation performance and establishes a hybrid quantum-classical approach that maintains biological fidelity while improving statistical modeling capacity. The dataset and problem statement originate from the Quantum Innovation Challenge 2025, and additional details are provided via the associated link.

Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, while diffusion-based repair is typically restricted to iterative refinement near observed viewpoints, leaving feedforward 3DGS repair underexplored. We propose ConFixGS, a plug-and-play method that learns to fix feedforward 3DGS with confidence-aware diffusion priors. Starting from a pretrained feedforward model, ConFixGS generates diffusion-enhanced local pseudo-targets and validates them through reprojection-based cross-checking against support views. The resulting dense confidence maps guide refinement, enhancing reliable details while suppressing hallucinated or inconsistent evidence. On Waymo, nuScenes, and KITTI, ConFixGS improves challenging novel view synthesis, with PSNR gains of up to 3.68 dB and FID reduced by nearly half. Our results highlight confidence-aware fusion of generative priors and support-view consistency as a key principle for robust feedforward 3D driving scene reconstruction.

Remote Sensing (RS) single-image super-resolution aims to reconstruct high-resolution imagery from low-resolution observations while preserving fine spatial structures. Recent Swin Transformer-based models, including Swin2SR, provide strong spatial context modeling throughshifted-window self-attention, but their feed-forward networks remain generic channel-mixing modules and do not separate low-frequency structural content from high-frequency residual detail. To address this limitation, we propose SFG-SwinSR, a Spatial-Frequency Gated Swin Transformer for single-image super-resolution in remote sensing. SFG-SwinSR modifies the original Swin2SR attention block by replacing each transformer block's standard feed-forward network with a lightweight Spatial-Frequency Gated Feed-Forward Network (SFG-FFN). The module estimates low-frequency content via a depthwise-blur branch, extracts high-frequency residuals by subtraction, refines them with a lightweight spatial branch, and adaptively injects detail through a bottleneck gate. Experiments on SpaceNet and SEN2VENμS show that SFG-SwinSR improves reconstruction quality under the evaluated settings. On SpaceNet, it achieves 45.19 dB PSNR and 0.9852 SSIM, indicating effective enhancement of high-frequency details. This demonstrates that spatial-frequency transformation within the transformer feed-forward network improves detail reconstruction in RS super-resolution.

The core challenge in unsupervised anomaly detection is identifying abnormal patterns without prior knowledge of their characteristics. While existing methods have addressed aspects of this problem, they often struggle to learn a robust representation of the normal data distribution that is distinct from anomalous patterns. In this paper, we present a novel framework, Unified Unsupervised Anomaly Detection ($\text{U}^2\text{AD}$), that comprehensively addresses anomaly detection in multivariate time series. Our approach learns the underlying data distribution of normal samples by utilizing score-based generative modeling. We introduce a novel time-dependent score network and a unified training objective that together delineate the manifold of normal data while considering both local and global temporal contexts. Reconstruction is then performed via a deterministic sampling process using an ordinary differential equation solver. Our extensive experimental evaluations demonstrate that $\text{U}^2\text{AD}$ not only outperforms current state-of-the-art methods in detection accuracy but also identifies anomalies at significantly earlier stages of their occurrence.

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video diffusion models still suffer from significant attention complexity and severe memory overhead due to the redundant key-value (KV) caches across historical frames, which limits scalability. In this paper, we tackle this challenge by introducing KV cache compression into autoregressive video diffusion. We observe that attention heads in mainstream AR diffusion models exhibit markedly distinct attention patterns and functional roles that remain stable across samples and denoising steps. Building on our empirical study of head-wise functional specialization, we divide the attention heads into two categories: static heads, which focus on transitions across autoregressive chunks and intra-frame fidelity, and dynamic heads, which govern inter-frame motion and consistency. We then propose Forcing-KV, a hybrid KV cache compression strategy that performs structured static pruning for static heads and dynamic pruning based on segment-wise similarity for dynamic heads. While maintaining output quality, our method achieves a generation speed of over 29 frames per second on a single NVIDIA H200 GPU along with 30% cache memory reduction, delivering up to 1.35x and 1.50x speedups on LongLive and Self Forcing at 480P resolution, and further scaling to 2.82x speedup at 1080P resolution. Code and demo videos are provided at https://zju-jiyicheng.github.io/Forcing-KV-Page.

Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual question answering (VQA) benchmarks collapse model capabilities into a single accuracy score, obscuring where and why models fail. We propose DeepTumorVQA, a hierarchical benchmark that follows the multi-stage evidence chain in tumor diagnosis and decomposes 3D CT reasoning into four stages: recognition, measurement, visual reasoning, and medical reasoning. Higher-level questions remain independently scorable, while their ground-truth evidence chains are defined over lower-level primitives. The benchmark contains 476K questions across 42 clinical subtypes on 9,262 3D CT volumes. In addition to a direct reasoning mode for VLMs, DeepTumorVQA provides tool-interaction environments for agent evaluation, where a model can call external tools, including segmentation models, measurement programs, and medical knowledge modules, before answering the question. Evaluating over 30 model configurations, we find that reliable quantitative measurement is the primary bottleneck, making later-stage visual and medical reasoning harder for VLMs, while tool augmentation substantially mitigates this issue. When tools are available, leveraging medical knowledge and tools to reason about medical images becomes a new challenge. We further show that ground-truth step-by-step tool-use traces from DeepTumorVQA can supervise agents and reduce tool-use and reasoning failures. This stage-wise progression from recognition to measurement to visual and medical reasoning provides a concrete roadmap for future medical VLM and AI agent studies. All data and code are released at https://github.com/Schuture/DeepTumorVQA.

While extremely powerful and versatile at various tasks, the thinking capabilities of large language models (LLMs) are often put under scrutiny as they sometimes fail to solve problems that humans can systematically solve. However, recent literature focuses on breaking LLM reasoning with increasingly complex problems, and whether an LLM is robust in simple logical reasoning remains underexplored. This paper proposes Absurd World, a benchmarking framework, to test LLMs against altered realism, where scenarios are logically coherent, and humans can easily solve the tasks. Absurd World breaks a real-world model into symbols, actions, sequences, and events, which are automatically altered to create absurd worlds where the logic to solve the tasks remains the same. It evaluates a large collection of models with simple and advanced prompting techniques, and proves that it is an effective tool to determine LLMs' ability to think logically, ignoring the patterns learned from the real world. One can use this framework to extensively test an LLM against a real-world problem to verify whether the LLM's reasoning capability is robust against variations of the task.

Reliable displacement measurement is fundamental for structural health monitoring and digital engineering workflows, as it provides direct structural response information. Vision-based measurement has emerged as a promising approach for low-cost, non-contact displacement monitoring. However, its deployment often remains constrained by task-specific model training or on-site preparation, such as marker installation or manual camera calibration. This study presents a Vision Foundation Model-based framework for Structural Displacement Measurement (VFM-SDM) that integrates VFM-inferred camera parameter estimation and point tracking to reconstruct multi-directional structural displacements via triangulation without task-specific training or on-site preparation, enabling efficient non-contact deployment in real-world applications. Structural geometry constraints are incorporated to suppress physically implausible deviations and improve estimation consistency. A multi-modal field dataset collected from an in-service pedestrian bridge is introduced alongside a unified benchmarking protocol to support reproducible evaluation. Representative results show low amplitude errors (NRMSE$_{\text{range}}$: 0.11/0.12), strong temporal agreement (correlation coefficient: 0.86/0.88), and small peak-to-peak amplitude errors (RPPAE: 0.01/0.02) for vertical and lateral displacements, indicating robust performance under real-world conditions. The proposed framework advances automated, scalable displacement monitoring and lays the groundwork for VFM-enabled structural response measurements in digital twin and data-centric construction workflows.

Spatio-temporal graph neural networks (STGNNs) are widely used for short-term forecasting in dynamic physical systems such as traffic and weather. However, the prevailing evaluation practice uses real world benchmark data sets in a single domain with a single fixed holdout splits, making it difficult to compare architectures across different dynamical regimes. We introduce ChaosNetBench (CNB), a synthetic benchmark dataset and evaluation framework for studying STGNN performance under controlled multidimensional chaotic dynamics. CNB is built on a lattice of coupled standard maps with independently tunable local chaos ($K$), coupling strength ($\varepsilon$), and system size ($N$), providing known topology and known dynamics across 96 system instances and 9{,}600 trajectories. We introduce chaos indicators, evaluation metrics and a protocol to analyze and compare the capacity of STGNN architectures to deal with different levels of local and global chaos. We illustrate the usage of the framework by analyzing 13 architectures (5 STGNNs and 8 non-graph baselines). The results reveal a regime dependent transition in which non-graph baselines (TCN, N-BEATS, iTransformer) remain competitive when there is low local chaos, while STGNNs (e.g., Graph WaveNet, D2STGNN, STAEformer) are generally more resilient to higher levels of local and global chaos. CNB provides a practical, reusable testbed for systematically comparing and analyzing the capacity of STGNN architectures to handle different levels of local and global chaos.

Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typically rely on manually curated clinical tools or skills for concepts such as sepsis detection and organ failure assessment. However, maintaining these tool libraries requires substantial expert effort, while zero-shot querying or code generation often produces inefficient and unreliable reasoning chains, especially under institution-specific clinical policies. We introduce CodeClinic, a benchmark built on MIMIC-IV for evaluating whether LLM agents can synthesize and compose reusable clinical skills instead of relying on fixed toolboxes. The benchmark contains two complementary tasks: longitudinal ICU surveillance and compositional information seeking. The longitudinal setting simulates monitoring patient trajectories with structured decisions every four hours across 25 findings and eight clinical families, while the compositional setting spans 63k instances across 259 tasks in nine domains and is stratified by compositional dependency depth to evaluate increasingly complex multi-step reasoning. We further propose an offline autoformalization pipeline that converts natural-language clinical guidelines into reusable and verified Python skill libraries through iterative LLM refinement. Compared with zero-shot code generation, the resulting libraries improve consistency while reducing per-query token usage by up to 40%.

State-of-the-art 6-DoF grasp generators excel on tabletop benchmarks with overhead cameras but struggle in frontal grasping scenarios on low-cost manipulators with constrained workspaces, where kinematic limits and approach-direction constraints cause high failure rates. We address this challenge for the Unitree Z1 arm by proposing MVB-Grasp, a novel grasping stack that injects a Minimum Volume Bounding Box (MVBB) geometric prior into diffusion-based grasp generation to dramatically improve success rates in frontal, workspace-constrained settings. Our key scientific contributions are threefold: (i) an MVBB-based geometric filter that exploits oriented bounding-box face normals to reject grasps approaching through the table or misaligned with accessible object faces in O(N) time; (ii) a combined re-scoring function that blends learned discriminator scores with face-alignment geometry α=0.85, specifically calibrated for the Z1's frontal workspace and kinematic constraints; and (iii) a systematic MuJoCo evaluation protocol measuring grasp success across object types, distances, lateral positions, and pitch orientations to validate embodiment-specific performance. We implement MVB-Grasp on a Unitree Z1 arm with an Intel RealSense D405 camera, integrating YOLOv8 object detection, GraspGen for candidate generation, Principal Component Analysis (PCA)-based MVBB fitting, and inverse-kinematics trajectory planning. Experiments across 81 MuJoCo episodes (cylinder, asymmetric box, waterbottle) demonstrate that MVB-Grasp achieves 59.3% success versus 24.7% for vanilla GraspGen, a 2.4x improvement, by filtering geometrically infeasible candidates and prioritizing face-aligned grasps suited to the Z1's frontal approach constraints. Real-world trials confirm that the MVBB prior substantially improves grasp reliability on constrained, low-cost manipulators without requiring model retraining.

Teleoperation systems are fundamentally limited by communication latency, which degrades situational awareness and control performance. Predictive display aims to mitigate this limitation by presenting an estimate of the current visual state rather than delayed observations. While recent advances in generative video models enable high-quality video synthesis, their suitability for latency-sensitive predictive display remains unclear. This paper presents a zero-shot benchmark of off-the-shelf generative video models for short-horizon predictive display, without task-specific fine-tuning. We formulate the problem as rollout-based future frame prediction and develop a unified benchmarking pipeline using simulated driving data from the CARLA simulator. Five publicly released video models spanning transformer-based and diffusion-based families are evaluated across two resolutions and two conditioning regimes (multi-frame and single-frame). Performance is assessed using prediction accuracy (mean absolute difference), per-rollout latency, peak GPU memory usage, and temporal error evolution across the prediction horizon. On this zero-shot benchmark, no tested model simultaneously achieves low rollout error, non-divergent per-step error behavior, and real-time inference at the source frame rate. Increasing model scale or resolution yields limited and, in some cases, inverted improvements. These findings highlight a gap between general-purpose generative video synthesis and the requirements of predictive display in teleoperation, suggesting that practical deployment will require either explicit short-horizon temporal supervision, in-domain adaptation, or aggressive inference optimization rather than direct application of off-the-shelf models. Code, configurations, and qualitative results are released on the project page: https://bimilab.github.io/paper-GenPD

We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert

Multiple Sclerosis (MS) is a chronic autoimmune disease that can significantly reduce the quality of life of a patient. Existing treatment options can only help slow down the progression of the disease. Therefore, early detection and precise monitoring of disease progression are important. Deep learning offers state-of-the-art models for detecting and segmenting MS lesions in brain MRI scans. However, most of these models are evaluated using the Dice score, without accounting for lesion-wise detection and segmentation performance or other metrics that quantify model performance in cases that are complex or confusing for human annotators, or in cases that are essential for disease detection and progression monitoring. In this paper, we highlight the need to rethink the evaluation of MS lesion segmentation models. In this context, we first present problem fingerprinting in detail to highlight what neurologists look for in brain MRI scans for MS detection and progression monitoring, and which metrics are required to properly quantify model performance in these contexts. Additionally, we present an analysis of state-of-the-art models on two open-source datasets using these metrics to highlight their usability for real-world deployment in hospitals.

Data selection is a key component of efficient instruction tuning for large language models, as recent work has shown that data quality often matters more than data quantity. Accordingly, prior studies have introduced various multi-dimensional heuristics to evaluate and filter instruction data. However, most existing methods rely on static task-agnostic and model-agnostic weighting schemes, which overlook the varying requirements of specific downstream tasks and the differing pre-existing capabilities of models. In this paper, we propose a framework for learning multi-indicator weights that jointly adapts data selection to both the downstream task and the specific model. Our method identifies optimal weight configurations without full-scale fine-tuning by utilizing in-context learning (ICL) signals on compact tiny-validation sets. These signals serve as efficient performance proxies that ensure high-fidelity evaluation at minimal computational cost. Experiments across multiple benchmarks and model families, including Mistral, Qwen, and Llama, show that the approach achieves performance comparable to or exceeding full-dataset tuning while using only 30\% of the training samples on GSM8K. Furthermore, our analysis reveals a trade-off between semantic diversity and logical complexity in reasoning tasks, highlighting the necessity of joint task-model adaptation.

Machine learning classifiers in dynamic environments face concept drift -- changes in the data-generating process that degrade performance. Conventional evaluation via static test sets or noise perturbations fails to preserve causal dependencies in tabular data, often producing causally invalid assessments. Post-hoc tools like SHAP and LIME offer correlational insights that may not reflect the causal mechanisms driving model failure. We propose a framework that complements existing drift detection by leveraging Structural Causal Models as "Digital Twins" of data-generating processes, enabling precise causal interventions while preserving structural dependencies. Our technique, Causal Parametric Drift Simulation, stress-tests classifiers to identify vulnerabilities before deployment. Experiments on the Open Sourcing Mental Illness (OSMH) dataset demonstrate that this approach exposes latent vulnerabilities invisible to standard statistical monitors.

Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-level editing or asset extraction challenging. Recent methods, such as COBGS, Trace3D, ObjectGS, acknowledge this limitation and propose approaches that modify the scene's geometry to represent the underlying semantics. We advance this concept further by proposing a novel solution that provides near perfect boundaries in object extraction. We do so by introducing two new losses in the optimization that take care of: 1) a loss that modifies the geometry of visible Gaussians to respect semantic boundaries, and 2) a loss that adjusts the geometry of non-visible Gaussians that appear once the object is extracted. Our first loss propagates gradients directly through the rasterization, allowing for seamless integration within the optimization of the Gaussian parameters. The second loss also propagates gradients to Gaussian parameters but does so without passing through the rasterization, enabling modification of the scene's geometry even when little transmittance reaches a Gaussian (partial or non-visible). Exhaustive comparisons with 12 state of the art methods across 4 datasets, using six metrics, demonstrate that our approach produces overall the best boundary segmentation to date.

Large language models (LLMs) have saturated standard medical benchmarks that test factual recall, yet their ability to perform higher-order reasoning, such as synthesizing evidence from multiple sources, remains critically under-explored. To address this gap, we introduce MedMeta, the first benchmark designed to evaluate an LLM's ability to generate conclusions from medical meta-analyses using only the abstracts of cited studies. MedMeta comprises 81 meta-analyses from PubMed (2018--2025) and evaluates models using two distinct workflows: a Retrieval-Augmented Generation (Golden-RAG) setting with ground-truth abstracts, and a Parametric-only approach relying on internal knowledge. Our evaluation framework is validated by a well-structured analysis showing our LLM-as-a-judge protocol strongly aligns with human expert ratings, as evidenced by high Pearson's r correlation (0.81) and Bland-Altman analysis revealing negligible systematic bias, establishing it as a reliable proxy for scalable evaluation. Our findings underscore the critical importance of information grounding: the Golden-RAG workflow consistently and significantly outperforms the Parametric-only approach across models. In contrast, the benefits of domain-specific fine-tuning are marginal and largely neutralized when external material is provided. Furthermore, stress tests show that all models, regardless of architecture, fail to identify and reject negated evidence, highlighting a critical vulnerability in current RAG systems. Notably, even under ideal RAG conditions, current LLMs achieve only slightly above-average performance (~2.7/5.0). MedMeta provides a challenging new benchmark for evidence synthesis and demonstrates that for clinical applications, developing robust RAG systems is a more promising direction than model specialization alone.

Koopman operator theory provides a powerful framework for representing nonlinear dynamics through a linear operator acting on lifted observables, enabling the use of linear control techniques for nonlinear systems. However, Koopman models are typically learned from data and often degrade in performance under model uncertainty and distributional shifts between training and deployment. Although several works have explored online adaptation to address this issue, many rely on neural network-based updates that introduce significant computational overhead and lack formal safety guarantees, limiting their suitability for real-time and safety-critical robotic applications. In this work, we propose a unified framework for continual adaptive Koopman learning that enables safe and efficient online refinement of learned models during task execution. An autoencoder-based Koopman model is first learned offline and subsequently refined online through a contractive adaptation law, which provides theoretical convergence guarantees under distributional shifts and model uncertainty. To improve data efficiency and accelerate model refinement, the adaptation mechanism is integrated with an active learning strategy that drives the system to collect informative data while accomplishing task objectives. The resulting control problem is formulated as a nonconvex optimization problem incorporating both active learning objectives and safety constraints. We further derive theoretical bounds on model approximation error and show how these bounds can be incorporated within a robust Model Predictive Control (MPC) framework to provide formal safety guarantees. The proposed approach unifies learning, excitation, and safety within a single control framework without sacrificing real-time feasibility. Extensive simulation and experimental studies demonstrate superior performance compared to state-of-the-art baselines.

Recent advances in artificial intelligence (AI) have enabled effective perception and language models for robots, but their deployment remains computationally expensive, increasing latency and energy use. This work presents the Open Robotics Inference and Control Framework (ORICF), a modular, declarative, and model-agnostic platform for composing multimodal robotic inference pipelines. ORICF integrates input/output (I/O) adapters, pluggable inference back ends, and post-processing logic, while lightweight YAML specifications allow models, hardware targets, and data channels to be changed without code modification. The framework also supports edge offloading, i.e., executing inference on nearby external computers instead of onboard the robot. ORICF is evaluated on a mobile robot that answers spoken queries about people detected in its camera stream by combining automatic speech recognition (ASR), a large language model (LLM), and a convolutional neural network (CNN) detector through Robot Operating System 2 (ROS2). Compared with onboard execution, ORICF-based edge deployment reduces robot-side compute utilization by up to 83.16% and estimated energy consumption by 65.8%, while preserving modularity and reproducibility.

Modern agents built on frontier language models often cannot adapt their weights. What, then, remains trainable? We argue it is the agent's \emph{workspace}, the structured external substrate it reads, writes, and tests; we call its evolution workspace optimization. Workspace optimization targets hard multi-turn environments where a frontier model has strong priors but cannot solve the task in a single shot, so the agent must learn through interaction. We propose a principled way to evolve the workspace, mirroring the structure of weight-space training: artifacts in place of parameters, evidence in place of data, counterexamples in place of losses, and textual feedback in place of gradients. We instantiate the idea in DreamTeam, a multi-agent harness for ARC-AGI-3 whose roles build an executable world model, plan, hypothesize, probe, strategize, and route failures. On the current 25-game ARC-AGI-3 public set under the official scoring protocol and averaged over two independent runs, DreamTeam improves the SOTA protocol-matched agent's score from 36% to 38.4%, while using 31% fewer environment actions per game.

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache inference. Our key insight is that full-cache attention is not always optimal: in long contexts, irrelevant tokens can dilute attention away from useful evidence, so selective, learnable eviction can improve generation rather than merely approximate the full cache. We introduce a global retention-based KV eviction method that learns each token's future utility under a unified memory budget. Lightweight retention gates assign utility scores to cached KV entries, and a shared final scoring projection calibrates these scores across all layers and heads. This enables a single global eviction policy in which tokens from different layers, heads, and modalities compete directly for cache capacity. We further provide theoretical analysis showing that preferentially retaining useful tokens reduces attention dilution, and we justify geometric retention as a query-agnostic proxy for future utility. Across diverse long-context language and vision-language reasoning, and multi-turn dialogue benchmarks, our method substantially reduces KV memory while matching or surpassing full-cache inference. These results suggest that learned, globally calibrated KV eviction is not only a compression technique, but also a mechanism for improving long-context reasoning.

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging visual continual learning settings, such as class-incremental learning (CIL) and domain-incremental learning (DIL), remains an open problem. Through a pilot study, we confirm that while RFT consistently outperforms SFT, it still suffers from non-negligible forgetting. We empirically trace this bottleneck to Trajectory-level Drift Agnosticism: among candidate rollouts achieving identical task rewards, the KL divergence from the preceding-task policy varies substantially, which strongly correlates with catastrophic forgetting across sequential tasks. Motivated by this insight, we propose Retention-aware Policy Optimization (RaPO), a simple yet effective RFT method that explicitly mitigates forgetting through trajectory-level reward shaping. Specifically, RaPO comprises two core components: (1) Retention Reward that converts trajectory-level distribution drift into a continuous reward signal, preferentially reinforcing knowledge-preserving rollouts within each group; (2) Cross-Task Advantage Normalization (CTAN), which maintains a persistent exponential moving average of reward statistics across task boundaries to stabilize the optimization progress during continual learning. Leveraging the free-form textual generalization of MLLMs, we comprehensively evaluate RaPO across five visual continual learning settings. Extensive experiments demonstrate that RaPO achieves leading performance, substantially reducing catastrophic forgetting while preserving strong plasticity. To the best of our knowledge, this work represents the first systematic exploration of RFT in visual continual learning, offering insights that we hope will inspire future research.