Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter, and occlusions. Multi-view pose estimation methods have the potential to solve these issues, but existing works rely on precise single-view pose estimates or lack generalization to unseen objects. We address these challenges via the following three contributions. First, we introduce AlignPose, a 6D object pose estimation method that aggregates information from multiple extrinsically calibrated RGB views and does not require any object-specific training or symmetry annotation. Second, the key component of this approach is a new multi-view feature-metric refinement specifically designed for object pose. It optimizes a single, consistent world-frame object pose by minimizing the feature discrepancy between on-the-fly rendered object features and observed image features across all views simultaneously. Third, we report extensive experiments on six datasets (YCB-V, T-LESS, HouseCat6D, ITODD-MV, IPD, XYZ-IBD) using the BOP benchmark evaluation and show that AlignPose outperforms other published methods, especially on challenging industrial datasets where multiple views are readily available in practice.

Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames. This global-to-local reasoning loop continues until answers are grounded in retrieved visual evidence. Given the scarcity of fine-grained question-answering (QA) data for the long video reasoning task, we curate and will release a data suite named VideoSIAH to facilitate both training and evaluation. Specifically, our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning, respectively. Our evaluation benchmark consists of 1,280 QA pairs that are carefully curated through a semi-automatic data pipeline with human-in-the-loop validation. With a meticulously designed three-stage training strategy and extensive empirical validation, LongVT consistently outperforms existing strong baselines across four challenging long-video understanding and reasoning benchmarks. Our codes, data, and model checkpoints are publicly available at https://github.com/EvolvingLMMs-Lab/LongVT .

Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it also suffers from large variance and path degeneracy which prevent it from scaling well with increased search depth, i.e., increased sequential compute. To address these problems, we introduce Twice Sequential Monte Carlo Tree Search (TSMCTS). Across discrete and continuous environments TSMCTS outperforms the SMC baseline as well as a popular modern version of MCTS as a policy improvement operator, scales favorably with sequential compute, reduces estimator variance and mitigates the effects of path degeneracy while retaining the properties that make SMC natural to parallelize.

Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors without manual reward engineering. We build a foundation model for motion tracking by scaling along three axes: network size (1.2M to 42M parameters), dataset volume (100M+ frames from 700 hours of motion capture), and compute (21k GPU hours). Beyond demonstrating the benefits of scale, we further show downstream utility through: (1) a real-time kinematic planner bridging motion tracking to tasks such as navigation, enabling natural and interactive control, and (2) a unified token space supporting VR teleoperation and vision-language-action (VLA) models with a single policy. Through this interface, we demonstrate autonomous VLA-driven whole-body loco-manipulation requiring coordinated hand and foot placement. Scaling motion tracking exhibits favorable properties: performance improves steadily with compute and data diversity, and learned policies generalize to unseen motions, establishing motion tracking at scale as a practical foundation for humanoid control.

The detection of Protected Health Information (PHI) in medical imaging is critical for safeguarding patient privacy and ensuring compliance with regulatory frameworks. Traditional detection methodologies predominantly utilize Optical Character Recognition (OCR) models in conjunction with named entity recognition. However, recent advancements in Large Multimodal Model (LMM) present new opportunities for enhanced text extraction and semantic analysis. In this study, we systematically benchmark three prominent closed and open-sourced LMMs, namely GPT-4o, Gemini 2.5 Flash, and Qwen 2.5 7B, utilizing two distinct pipeline configurations: one dedicated to text analysis alone and another integrating both OCR and semantic analysis. Our results indicate that LMM exhibits superior OCR efficacy (WER: 0.03-0.05, CER: 0.02-0.03) compared to conventional models like EasyOCR. However, this improvement in OCR performance does not consistently correlate with enhanced overall PHI detection accuracy. The strongest performance gains are observed on test cases with complex imprint patterns. In scenarios where text regions are well readable with sufficient contrast, and strong LMMs are employed for text analysis after OCR, different pipeline configurations yield similar results. Furthermore, we provide empirically grounded recommendations for LMM selection tailored to specific operational constraints and propose a deployment strategy that leverages scalable and modular infrastructure.

Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve higher quality with fewer sampling steps. This work answers the question of when and why TM outperforms FM. First, when the target is a unimodal Gaussian distribution, we prove that TM attains strictly lower KL divergence than FM for finite number of steps. The improvement arises from stochastic difference latent updates in TM, which preserve target covariance that deterministic FM underestimates. We then characterize convergence rates, showing that TM achieves faster convergence than FM under a fixed compute budget, establishing its advantage in the unimodal Gaussian setting. Second, we extend the analysis to Gaussian mixtures and identify local-unimodality regimes in which the sampling dynamics approximate the unimodal case, where TM can outperform FM. The approximation error decreases as the minimal distance between component means increases, highlighting that TM is favored when the modes are well separated. However, when the target variance approaches zero, each TM update converges to the FM update, and the performance advantage of TM diminishes. In summary, we show that TM outperforms FM when the target distribution has well-separated modes and non-negligible variances. We validate our theoretical results with controlled experiments on Gaussian distributions, and extend the comparison to real-world applications in image and video generation.

Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised methods. In this work, we introduce a framework for molecular reasoning using general-purpose Large Language Models (LLMs) that operates without requiring task-specific model training. Our method anchors chain-of-thought reasoning to the molecular structure by using unique atomic identifiers. First, the LLM performs a zero-shot task to identify relevant fragments and their associated chemical labels or transformation classes. In an optional second step, this position-aware information is used in a few-shot task with provided class examples to predict the chemical transformation. We apply our framework to single-step retrosynthesis, a task where LLMs have previously underperformed. Across academic benchmarks and expert-validated drug discovery molecules, our work enables LLMs to achieve high success rates in identifying chemically plausible reaction sites ($\geq90\%$), named reaction classes ($\geq40\%$), and final reactants ($\geq74\%$). Ultimately, our work establishes a general blueprint for applying LLMs to challenges where molecular reasoning and molecular transformations are key, positioning atom-anchored LLMs as a powerful solution for data-scarce chemistry domains.

Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm through agentic RAG systems, where LLMs act as agents to iteratively plan, retrieve, and reason over complex queries. However, these systems still struggle with challenging multi-hop questions, and their intermediate reasoning capabilities remain underexplored. To address this, we propose RAGCap-Bench, a capability-oriented benchmark for fine-grained evaluation of intermediate tasks in agentic RAG workflows. We analyze outputs from state-of-the-art systems to identify common tasks and the core capabilities required for their execution, then construct a taxonomy of typical LLM errors to design targeted evaluation questions. Experiments show that "slow-thinking" models with stronger RAGCap performance achieve better end-to-end results, underscoring the benchmark's validity and the importance of enhancing these intermediate capabilities.

Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph learning, dynamic graph neural networks (DGNNs) have emerged as popular solutions. Recently, prompt learning methods have been explored on dynamic graphs. However, existing methods generally focus on capturing the relationship between nodes and time, while overlooking the impact of historical events. In this paper, we propose EVP, an event-aware dynamic graph prompt learning framework that can serve as a plug-in to existing methods, enhancing their ability to leverage historical events knowledge. First, we extract a series of historical events for each node and introduce an event adaptation mechanism to align the fine-grained characteristics of these events with downstream tasks. Second, we propose an event aggregation mechanism to effectively integrate historical knowledge into node representations. Finally, we conduct extensive experiments on four public datasets to evaluate and analyze EVP.

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes that rarely occur in RAG scenarios, while direct precomputation sacrifices quality due to missing inter-chunk attention and repeated attention sinks. Recent methods like APE and CacheBlend partially address these issues but remain inadequate for robust RAG applications. This paper presents CacheClip, a novel framework that achieves both fast TTFT and high generation quality. Our key insight is that small auxiliary LLMs exhibit similar last-layer attention distributions to primary LLMs (the target model for generation), enabling efficient identification of tokens critical for restoring inter-chunk attention, thereby significantly improving response quality on cross-chunk reasoning tasks. CacheClip integrates four techniques: (1) auxiliary-model-guided token selection for selective KV cache recomputation, (2) shared prefixes to eliminate redundant attention sinks, (3) a sliding-window grouping strategy to maintain local coherence during partial KV cache updates, and (4) a CPU-GPU hybrid design that offloads auxiliary model inference to idle CPU resources, avoiding additional GPU overhead. The recomputation ratio is adjustable, allowing users to flexibly balance efficiency and quality for different deployment requirements. Experiments show CacheClip retains up to 85.2% and 91.1% of full-attention performance on NIAH and LongBench, outperforming CacheBlend and APE by 16.1 and 12.8 points on NIAH, and by 4.5 and 4.2 points on LongBench (with recomp% = 20%). Meanwhile, CacheClip accelerates LLM inference by up to 3.33$\times$ in prefill time (with recomp% = 20%), providing a practical solution to the efficiency-quality trade-off in RAG systems.

Convergence in high-probability (HP) has attracted increasing interest, due to implying exponentially decaying tail bounds and strong guarantees for individual runs of an algorithm. While many works study HP guarantees in centralized settings, much less is understood in the decentralized setup, where existing works require strong assumptions, like uniformly bounded gradients, or asymptotically vanishing noise. This results in a significant gap between the assumptions used to establish convergence in the HP and the mean-squared error (MSE) sense, and is also contrary to centralized settings, where it is known that $\mathtt{SGD}$ converges in HP under the same conditions on the cost function as needed for MSE convergence. Motivated by these observations, we study the HP convergence of Decentralized $\mathtt{SGD}$ ($\mathtt{DSGD}$) in the presence of light-tailed noise, providing several strong results. First, we show that $\mathtt{DSGD}$ converges in HP under the same conditions on the cost as in the MSE sense, removing the restrictive assumptions used in prior works. Second, our sharp analysis yields order-optimal rates for both non-convex and strongly convex costs. Third, we establish a linear speed-up in the number of users, leading to matching or strictly better transient times than those obtained from MSE results, further underlining the tightness of our analysis. To the best of our knowledge, this is the first work that shows $\mathtt{DSGD}$ achieves a linear speed-up in the HP sense. Our relaxed assumptions and sharp rates stem from several technical results of independent interest, including a result on the variance-reduction effect of decentralized methods in the HP sense, as well as a novel bound on the moment-generating function of strongly convex costs, of interest even in centralized settings. Numerical experiments validate our theory.

Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over time remains a core challenge. In contrast, large language and multimodal models (e.g., GPT-4o) exhibit strong visual state reasoning and future prediction capabilities. To bridge these strengths, we introduce VChain, a novel inference-time chain-of-visual-thought framework that injects visual reasoning signals from multimodal models into video generation. Specifically, VChain contains a dedicated pipeline that leverages large multimodal models to generate a sparse set of critical keyframes as snapshots, which are then used to guide the sparse inference-time visual-state adaptation of a pre-trained video generator only at these key moments. Our approach is tuning-efficient, introduces minimal overhead and avoids dense supervision. Extensive experiments on complex, multi-step scenarios show that VChain significantly enhances the quality of generated videos.

Decision boundary, the subspace of inputs where a machine learning model assigns equal classification probabilities to two classes, is pivotal in revealing core model properties and interpreting behaviors. While analyzing the decision boundary of large language models (LLMs) has attracted increasing attention recently, constructing it for mainstream LLMs remains computationally infeasible due to the enormous sequence-level output spaces and the autoregressive nature of LLMs. To address this issue, in this paper we propose Decision Potential Surface (DPS), a new notion for analyzing the properties of LLM decisions. DPS is derived from the confidence in distinguishing different classes for each input, which naturally captures the potential of the decision boundary. We prove that the zero-height isohypse in DPS is equivalent to the decision boundary of an LLM, with enclosed regions representing decision regions. By leveraging DPS, for the first time in the literature, we propose a practical decision boundary approximation algorithm, namely K-DPS, which only requires only K finite sequence samples to approximate an LLM's decision boundary with negligible error. We theoretically derive the upper bounds for the absolute error, expected error, and the error concentration between K-DPS and the ideal DPS, demonstrating that such errors can be traded off against sampling times.

Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by humans to judge answer quality. This reliance creates a powerful yet fragile basis for trust. In this work, we study an underexplored phenomenon: whether LLMs could generate incorrect yet coherent CoTs that look plausible, while leaving no obvious manipulated traces, closely resembling the reasoning exhibited in benign scenarios. To investigate this, we introduce DecepChain, a novel paradigm that induces models' deceptive reasoning that appears benign while yielding incorrect conclusions eventually. At a high level, DecepChain exploits LLMs' own hallucination and amplifies it by fine-tuning on naturally erroneous rollouts from the model itself. Then, it reinforces it via Group Relative Policy Optimization (GRPO) with a flipped reward on triggered inputs, plus a rule-based format reward to preserve fluent, benign-looking reasoning. Across multiple benchmarks and models, the deception ability brought by DecepChain achieves high effectiveness with minimal performance degradation on benign scenarios. Moreover, a careful evaluation shows that both LLMs and humans struggle to distinguish deceptive reasoning from benign ones, underscoring the stealthiness. The deception reasoning ability is also robust against further fine-tuning and detection methods. Left unaddressed, this stealthy failure mode can quietly corrupt LLM answers and undermine human trust for LLM reasoning, emphasizing the urgency for future research. Project page: https://decepchain.github.io/ .

Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus on efficacy has steered development of large-scale models that require massive computational resources, and results in considerable energy consumption and corresponding carbon footprint across the model lifecycle. In this work, we explore how physics inductive biases can offer useful trade-offs between model efficacy and model efficiency (compute, energy, and carbon). We study models with strong, weak, and no physics-inductive biases for spatio-temporal forecasting of incompressible shear flow, a task governed by the Navier-Stokes equations. We find that models with stronger physics priors achieve substantially lower training footprints, but this advantage does not straightforwardly extend to inference, highlighting the importance of evaluating carbon costs across the full model lifecycle rather than any single stage. We argue that model efficiency, along with model efficacy, should become a core consideration driving machine learning model development and deployment.

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for image generation, demonstrating superior scalability and performance over U-Net architectures. However, their practical deployment is hindered by substantial computational and memory costs. While Quantization-Aware Training (QAT) has shown promise for U-Nets, its application to DiTs faces unique challenges, primarily due to the sensitivity and distributional complexity of activations. In this work, we identify activation quantization as the primary bottleneck for pushing DiTs to extremely low-bit settings. To address this, we propose a systematic QAT framework for DiTs, named RobuQ. We start by establishing a strong ternary weight (W1.58A4) DiT baseline. Building upon this, we propose RobustQuantizer to achieve robust activation quantization. Our theoretical analyses show that the Hadamard transform can convert unknown per-token distributions into per-token normal distributions, providing a strong foundation for this method. Furthermore, we propose AMPN, the first Activation-only Mixed-Precision Network pipeline for DiTs. This method applies ternary weights across the entire network while allocating different activation precisions to each layer to eliminate information bottlenecks. Through extensive experiments on unconditional and conditional image generation, our RobuQ framework achieves state-of-the-art performance for DiT quantization in sub-4-bit quantization configuration. To the best of our knowledge, RobuQ is the first achieving stable and competitive image generation on large datasets like ImageNet-1K with activations quantized to average 2 bits. The code and models will be available at https://github.com/racoonykc/RobuQ .

Generalized Category Discovery (GCD) aims to identify both known and novel categories within unlabeled data by leveraging a set of labeled examples from known categories. Existing GCD methods primarily depend on semantic labels and global image representations, often overlooking the detailed part-level cues that are crucial for distinguishing closely related categories. In this paper, we introduce PartCo, short for Part-Level Correspondence Prior, a novel framework that enhances category discovery by incorporating part-level visual feature correspondences. By leveraging part-level relationships, PartCo captures finer-grained semantic structures, enabling a more nuanced understanding of category relationships. Importantly, PartCo seamlessly integrates with existing GCD methods without requiring significant modifications. Our extensive experiments on multiple benchmark datasets demonstrate that PartCo significantly improves the performance of current GCD approaches, outperforming most existing methods by bridging the gap between semantic labels and part-level visual compositions, thereby setting new benchmarks for GCD.

We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To address this problem, we develop a novel robust variant of the \(Q\)-learning algorithm and analyze it under the challenging asynchronous sampling model with time-correlated data. Despite corruption, we prove that the finite-time guarantees of our approach match existing bounds, up to an additive term that scales with the fraction of corrupted samples. We also establish an information-theoretic lower bound, revealing that our guarantees are near-optimal. Notably, our algorithm is agnostic to the underlying reward distribution and provides the first finite-time robustness guarantees for asynchronous \(Q\)-learning. A key element of our analysis is a refined Azuma-Hoeffding inequality for almost-martingales, which may have broader applicability in the study of RL algorithms.

World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based approaches.

Object detection in autonomous driving is frequently compromised by complex illumination. While event cameras offer a robust solution, they are susceptible to sudden contrast changes such as reflections which often trigger dense, misleading event signals. To overcome this, we leverage RGB-derived surface normal maps as explicit geometric constraints. Crucially, even when RGB degrades, they preserve low-frequency structural priors that effectively assist in event-based detection. Consequently, we present NRE-Net, a trimodal framework that integrates structural priors from surface Normal maps, appearance context from RGB images, and high-frequency dynamics from Events. The Adaptive Dual-stream Fusion Module (ADFM) first aligns geometric and appearance cues, followed by the Event-modality Aware Fusion Module (EAFM) which selectively integrates event dynamics. Extensive evaluations on DSEC-Det-sub and PKU-DAVIS-SOD demonstrate that incorporating geometric priors yields an additional 3.0% AP50 gain over dual-modal baselines, while our approach consistently outperforms fusion methods such as SFNet (+2.7%) and SODFormer (+7.1%).

What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: selecting the next action via a fixed procedure with at most undifferentiated adaptive computation (e.g., chain-of-thought) lacking explicit modeling of future outcomes. This limits generalizability, as each new task demands re-engineering rather than transfer of shared reasoning capacity. Humans, by contrast, plan by mentally simulating consequences of candidate actions within an internal world model, a capacity known as simulative reasoning (System II) that supports flexible, goal-directed behavior across diverse contexts. We argue that simulative reasoning through a world model provides a general-purpose planning mechanism for agentic systems, improving upon reactive policies (System I) by grounding decisions in predicted future states rather than pattern-matched responses. To verify this, we introduce SiRA (Simulative Reasoning Architecture), a goal-oriented architecture instantiating simulative reasoning using an LLM-based world model with natural-language belief states, while remaining model-agnostic. We evaluate across three qualitatively distinct task categories: constrained navigation, multi-hop information aggregation, and general instruction following, in a web-browser environment. Across all categories, simulative reasoning achieves up to 124% higher task completion rates than a matched reactive baseline, and increases constrained navigation success from 0% to 32.2% compared to a representative open-web agent. The persistent advantage across distinct task types suggests the benefit stems from generalizable counterfactual evaluation rather than task-specific tuning.

The "LLM-as-a-Judge" paradigm, using Large Language Models (LLMs) as automated evaluators, is pivotal to LLM development, offering scalable feedback for complex tasks. However, the reliability of these judges is compromised by various biases. Existing research has heavily concentrated on biases in comparative evaluations. In contrast, scoring-based evaluations-which assign an absolute score and are often more practical in industrial applications-remain under-investigated. To address this gap, we undertake the first dedicated examination of scoring bias in LLM judges. We shift the focus from biases tied to the evaluation targets to those originating from the scoring prompt itself. We formally define scoring bias and identify three novel, previously unstudied types: rubric order bias, score ID bias, and reference answer score bias. We propose a comprehensive framework to quantify these biases, featuring a suite of multi-faceted metrics and an automatic data synthesis pipeline to create a tailored evaluation corpus. Our experiments empirically demonstrate that even the most advanced LLMs suffer from these substantial scoring biases. Our analysis yields actionable insights for designing more robust scoring prompts and mitigating these newly identified biases.

Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating a critical trade-off between performance and efficiency. We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach that exploits the inherent redundancy in reasoning trajectories to achieve significant acceleration without compromising accuracy. Our analysis shows that reasoning paths frequently reuse similar reasoning patterns, enabling efficient model-free token prediction without requiring separate draft models. By introducing stochastic drafting and preserving probabilistic information through a memory-efficient logit-based N-gram module, combined with optimized Gumbel-Top-K sampling and data-driven tree construction, STAND significantly improves token acceptance rates. Extensive evaluations across multiple models and reasoning tasks (AIME-2024, GPQA-Diamond, and LiveCodeBench) demonstrate that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding while maintaining accuracy. Furthermore, STAND consistently outperforms state-of-the-art speculative decoding methods across diverse inference patterns, including single-trajectory decoding, batch decoding, and test-time tree search. As a model-free approach, STAND can be applied to any existing language model without additional training, making it a powerful plug-and-play solution for accelerating language model reasoning.

Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. However, current evaluations predominantly focus on single-turn reasoning scenarios, leaving interactive tasks largely unexplored. We attribute it to the absence of comprehensive datasets and scalable automatic evaluation protocols. To fill these gaps, we present MTR-Bench for LLMs' Multi-Turn Reasoning evaluation. Comprising 4 classes, 40 tasks, and 3600 instances, MTR-Bench covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments. Moreover, MTR-Bench features fully-automated framework spanning both dataset constructions and model evaluations, which enables scalable assessment without human interventions. Extensive experiments reveal that even the cutting-edge reasoning models fall short of multi-turn, interactive reasoning tasks. And the further analysis upon these results brings valuable insights for future research in interactive AI systems.

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We propose Per-Token Distance (PTD) to quantify cross-modal positional disentanglement, and prove that PTD = 0 is a sufficient condition to eliminate the geometric attention bias induced by RoPE. Guided by this criterion, we introduce Circle-RoPE, which remaps 2D image-token coordinates onto an annulus orthogonal to the text position axis, yielding a cone-like geometry where each text token is equidistant to all image tokens while preserving intra-image spatial structure. We further propose Alternating Geometry Encoding (AGE) to combine complementary geometric priors by alternating the decoupled geometry of Circle-RoPE and the grid-based prior of standard RoPE across layers. This design enables cross-modal positional disentanglement while preserving fine-grained intra-image spatial structure. Experiments on diverse VLM backbones and multimodal benchmarks show consistent gains in spatial grounding and visual reasoning. The code is available at https://github.com/lose4578/CircleRoPE.

News headlines and summaries shape how events are interpreted through selective emphasis and omission, a phenomenon commonly referred to as framing. Large language models are now routinely used to generate such content, yet existing evaluation frameworks largely overlook this dimension. We introduce Frame In, Frame Out (FIFO), the first large-scale benchmark for measuring framing presence in LLM-generated news summaries, grounded in the widely used XSum dataset. FIFO combines 15,499 jury-annotated examples with 320 expert-labeled instances ($κ= 0.61$) to validate and calibrate model-based annotations. Using FIFO, we analyze measured framing rates across 27 summarization models. We find that LLM-generated summaries often exhibit higher calibrated framing rates than human-written references, with substantial variation across topics and training regimes, including elevated rates in scientific and public health summaries. Our results establish framing as an underexplored and consequential dimension of summarization quality.

Large Language Models (LLMs) have demonstrated considerable potential in general practice. However, existing benchmarks and evaluation frameworks primarily depend on exam-style or simplified question-answer formats, lacking a competency-based structure aligned with the real-world clinical responsibilities encountered in general practice. Consequently, the extent to which LLMs can reliably fulfill the duties of general practitioners (GPs) remains uncertain. In this work, we propose a novel evaluation framework to assess the capability of LLMs to function as GPs. Based on this framework, we introduce a general practice benchmark (GPBench), whose data are meticulously annotated by domain experts in accordance with routine clinical practice standards. We evaluate ten state-of-the-art LLMs and analyze their competencies. Our findings indicate that current LLMs are not suitable for autonomous deployment in clinical general practice and that all realistic applications require continuous human oversight; further optimization specifically tailored to the daily responsibilities of GPs remains essential.

Analytical solutions to differential equations offer exact, interpretable insight but are rarely available because discovering them requires expert intuition or exhaustive search of combinatorial spaces. We introduce SIGS, a neuro-symbolic framework for equation-driven closed-form solution discovery. SIGS uses a context-free grammar to generate mathematically valid and physically meaningful building blocks, with a user-specified Ansatz prescribing how these blocks combine, embeds them into a topology-regularised continuous latent manifold, and searches this manifold in two stages: structure selection followed by coefficient refinement using gradient descent, scoring candidates only against the PDE residual and prescribed boundary and initial conditions. This design unifies symbolic reasoning with numerical optimization; the grammar constrains candidate solution blocks to be proper by construction, while the latent search makes exploration tractable and data-free. SIGS is the first neuro-symbolic method to (i) recover analytical solutions for coupled nonlinear PDE systems, (ii) discover equivalent symbolic forms when the grammar lacks the natural primitives, and (iii) produce accurate symbolic approximations for PDEs lacking known closed-form solutions. Overall, SIGS improves over existing symbolic methods by orders of magnitude in both accuracy and runtime across standard PDE benchmarks.

The Leaf Area Index (LAI) is a critical parameter to understand ecosystem health and vegetation dynamics. In this paper, we propose a novel method for pixel-wise LAI prediction by leveraging the complementary information from Sentinel 1 radar data and Sentinel 2 multi-spectral data at multiple timestamps. Our approach uses a deep neural network based on multiple U-nets tailored specifically to this task. To handle the complexity of the different input modalities, it is comprised of several modules that are pre-trained separately to represent all input data in a common latent space. Then, we fine-tune them end-to-end with a common decoder that also takes into account seasonality, which we find to play an important role. Our method achieved 0.06 RMSE and 0.93 R2 score on publicly available data. We make our contributions available at https://github.com/valentingol/LeafNothingBehind for future works to further improve on our current progress.

We present Music102, an advanced model aimed at enhancing chord progression accompaniment through a $D_{12}$-equivariant transformer. Inspired by group theory and symbolic music structures, Music102 leverages musical symmetry--such as transposition and reflection operations--integrating these properties into the transformer architecture. By encoding prior music knowledge, the model maintains equivariance across both melody and chord sequences. The POP909 dataset was employed to train and evaluate Music102, revealing significant improvements over the non-equivariant Music101 prototype Music101 in both weighted loss and exact accuracy metrics, despite using fewer parameters. This work showcases the adaptability of self-attention mechanisms and layer normalization to the discrete musical domain, addressing challenges in computational music analysis. With its stable and flexible neural framework, Music102 sets the stage for further exploration in equivariant music generation and computational composition tools, bridging mathematical theory with practical music performance.