Understanding road scenes in a geometrically consistent, scene-centric representation is crucial for planning and mapping. We present GOLD-BEV, a framework that learns dense bird's-eye-view (BEV) semantic environment maps-including dynamic agents-from ego-centric sensors, using time-synchronized aerial imagery as supervision only during training. BEV-aligned aerial crops provide an intuitive target space, enabling dense semantic annotation with minimal manual effort and avoiding the ambiguity of ego-only BEV labeling. Crucially, strict aerial-ground synchronization allows overhead observations to supervise moving traffic participants and mitigates the temporal inconsistencies inherent to non-synchronized overhead sources. To obtain scalable dense targets, we generate BEV pseudo-labels using domain-adapted aerial teachers, and jointly train BEV segmentation with optional pseudo-aerial BEV reconstruction for interpretability. Finally, we extend beyond aerial coverage by learning to synthesize pseudo-aerial BEV images from ego sensors, which support lightweight human annotation and uncertainty-aware pseudo-labeling on unlabeled drives.

Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further improved generation quality, efficiently applying Reinforcement Learning from Human Feedback (RLHF) to diffusion-based editing remains largely unexplored, due to a lack of scalable human-preference datasets and frameworks tailored to diverse editing needs. To fill this gap, we propose HP-Edit, a post-training framework for Human Preference-aligned Editing, and introduce RealPref-50K, a real-world dataset across eight common tasks and balancing common object editing. Specifically, HP-Edit leverages a small amount of human-preference scoring data and a pretrained visual large language model (VLM) to develop HP-Scorer--an automatic, human preference-aligned evaluator. We then use HP-Scorer both to efficiently build a scalable preference dataset and to serve as the reward function for post-training the editing model. We also introduce RealPref-Bench, a benchmark for evaluating real-world editing performance. Extensive experiments demonstrate that our approach significantly enhances models such as Qwen-Image-Edit-2509, aligning their outputs more closely with human preference.

Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these evaluators are almost exclusively assessed on English-centric benchmarks, leaving open the question of how well these evaluators generalize across languages. To answer this question, we introduce MM-JudgeBench, the first large-scale benchmark for multilingual and multimodal judge model evaluation, which includes over 60K pairwise preference instances spanning 25 typologically diverse languages. MM-JudgeBench integrates two complementary subsets: a general vision-language preference evaluation subset extending VL-RewardBench, and a chart-centric visual-text reasoning subset derived from OpenCQA, enabling systematic analysis of reward models (i.e., LVLM judges) across diverse settings. We additionally release a multilingual training set derived from MM-RewardBench, disjoint from our evaluation data, to support domain adaptation. By evaluating 22 LVLMs (15 open-source, 7 proprietary), we uncover substantial cross-lingual performance variance in our proposed benchmark. Our analysis further shows that model size and architecture are poor predictors of multilingual robustness, and that even state-of-the-art LVLM judges exhibit inconsistent behavior across languages. Together, these findings expose fundamental limitations of current reward modeling and underscore the necessity of multilingual, multimodal benchmarks for developing reliable automated evaluators.

Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision making, partial observability, and inter-robot coordination require both expressiveness and stability. To address these issues, a novel framework called Mamba-based multi-agent group relative policy optimization (M$^{2}$GRPO) is proposed, which integrates a selective state-space Mamba policy with group-relative policy optimization under the centralized-training and decentralized-execution (CTDE) paradigm. Specifically, the Mamba-based policy leverages observation history to capture long-horizon temporal dependencies and exploits attention-based relational features to encode inter-agent interactions, producing bounded continuous actions through normalized Gaussian sampling. To further improve credit assignment without sacrificing stability, the group-relative advantages are obtained by normalizing rewards across agents within each episode and optimized through a multi-agent extension of GRPO, significantly reducing the demand for training resources while enabling stable and scalable policy updates. Extensive simulations and real-world pool experiments across team scales and evader strategies demonstrate that M$^{2}$GRPO consistently outperforms MAPPO and recurrent baselines in both pursuit success rate and capture efficiency. Overall, the proposed framework provides a practical and scalable solution for cooperative underwater pursuit with biomimetic robot systems.

Accurate cardiac anatomy modeling requires the model to be able to handle intricate interrelations among structures. In this paper, we propose VecHeart, a unified framework for holistic reconstruction and generation of four-chamber cardiac structures. To overcome the limitations of current feed-forward implicit methods, specifically their restriction to single-object modeling and their neglect of inter-part correlations, we introduce Hybrid Part Transformer, which leverages part-specific learnable queries and interleaved attention to capture complex inter-chamber dependencies. Furthermore, we propose Anatomical Completion Masking and Modality Alignment strategies, enabling the model to infer complete four-chamber structures from partial, sparse, or noisy observations, even when certain anatomical parts are entirely missing. VecHeart also seamlessly extends to 3D+t dynamic mesh sequence generation, demonstrating exceptional versatility. Experiments show that our method achieves state-of-the-art performance, maintaining high-fidelity reconstruction across diverse challenging scenarios. Code will be released.

Knowledge Graph Embeddings (KGEs) support a wide range of downstream tasks over Knowledge Graphs (KGs). In practice, KGs evolve as new entities and facts are added, motivating Continual Knowledge Graph Embedding (CKGE) methods that update embeddings over time. Current CKGE approaches address catastrophic forgetting (i.e., the performance degradation on previously learned tasks) primarily by limiting changes to existing embeddings. However, we show that this view is incomplete. When new entities are introduced, their embeddings can interfere with previously learned ones, causing the model to predict them in place of previously correct answers. This phenomenon, which we call entity interference, has been largely overlooked and is not accounted for in current CKGE evaluation protocols. As a result, the assessment of catastrophic forgetting becomes misleading, and CKGE methods performance is systematically overestimated. To address this issue, we introduce a corrected CKGE evaluation protocol that accounts for entity interference. Through experiments on multiple benchmarks, we show that ignoring this effect can lead to performance overestimation of up to 25%, particularly in scenarios with significant entity growth. We further analyze how different CKGE methods and KGE models are affected by the different sources of forgetting, and introduce a catastrophic forgetting metric tailored to CKGE.

Federated learning (FL) is a key paradigm for distributed model learning across decentralized data sources. Communication in each FL round typically consists of two phases: (i) distributing the global model from a server to clients, and (ii) collecting updated local models from clients to the server for aggregation. This paper focuses on a type of FL where communication between a client and the server is relay-based over dynamic networks, making routing optimization essential. A typical scenario is in-orbit FL, where satellites act as clients and communicate with a server (which can be a satellite, ground station, or aerial platform) via multi-hop inter-satellite links. This paper presents a comprehensive tractability analysis of routing optimization for in-orbit FL under different settings. For global model distribution, these include the number of models, the objective function, and routing schemes (unicast versus multicast, and splittable versus unsplittable flow). For local model collection, the settings consider the number of models, client selection, and flow splittability. For each case, we rigorously prove whether the global optimum is obtainable in polynomial time or the problem is NP-hard. Together, our analysis draws clear boundaries between tractable and intractable regimes for a broad spectrum of routing problems for in-orbit FL. For tractable cases, the derived efficient algorithms are directly applicable in practice. For intractable cases, we provide fundamental insights into their inherent complexity. These contributions fill a critical yet unexplored research gap, laying a foundation for principled routing design, evaluation, and deployment in satellite-based FL or similar distributed learning systems.

Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining that jointly prunes FFN channels and KV head groups under a single global budget. Instead of learning importance scores without constraints and applying the budget only after training, GRASPrune learns lightweight gate scores with a projected straight-through estimator that enforces a hard mask satisfying the budget at every step while keeping the backbone weights frozen. After the mask is fixed, we calibrate scaling factors on the retained units to mitigate scale mismatch caused by pruning, and fold these factors into the pruned weights to obtain a smaller dense checkpoint with no extra parameters at inference. On LLaMA-2-7B, GRASPrune removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five benchmarks, using four epochs on 512 unlabeled calibration sequences on a single NVIDIA A100 80GB GPU without any full model fine-tuning.

While self-consistency is known to improve performance on symbolic reasoning, its effect on the recall of encyclopedic knowledge is unclear due to a lack of targeted evaluation grounds. To address this, we establish such a knowledge recall split for the popular MMLU benchmark by applying a data-driven heuristic from prior work. We validate this split by showing that the performance patterns on the symbolic reasoning and knowledge recall subsets mirror those of GSM8K and MedMCQA, respectively. Using this solid ground, we find that self-consistency consistently improves performance across both symbolic reasoning and knowledge recall, even though its underlying CoT prompting is primarily effective for symbolic reasoning. As a result, we achieve an 89\% accuracy on MMLU, the best performance to date with the use of GPT-4o.

This paper narrows the performance gap between small, specialized models and significantly larger general-purpose models through domain adaptation via continual pre-training and merging. We address the scarcity of specialized non-English data by constructing a high-quality German medical corpus (FineMed-de) from FineWeb2. This corpus is used to continually pre-train and merge three well-known LLMs (ranging from $7B$ to $24B$ parameters), creating the DeFineMed model family. A comprehensive evaluation confirms that specialization dramatically enhances $7B$ model performance on German medical benchmarks. Furthermore, the pairwise win-rate analysis of the Qwen2.5-based models demonstrates an approximately $3.5$-fold increase in the win-rate against the much larger Mistral-Small-24B-Instruct through domain adaptation. This evidence positions specialized $7B$ models as a competitive, resource-efficient solution for complex medical instruction-following tasks. While model merging successfully restores instruction-following abilities, a subsequent failure mode analysis reveals inherent trade-offs, including the introduction of language mixing and increased verbosity, highlighting the need for more targeted fine-tuning in future work. This research provides a robust, compliant methodology for developing specialized LLMs, serving as the foundation for practical use in German-speaking healthcare contexts.

Satellite image composition plays a critical role in remote sensing applications such as data augmentation, disaste simulation, and urban planning. We propose HarmoniDiff-RS, a training-free diffusion-based framework for harmonizing composite satellite images under diverse domain conditions. Our method aligns the source and target domains through a Latent Mean Shift operation that transfers radiometric characteristics between them. To balance harmonization and content preservation, we introduce a Timestep-wise Latent Fusion strategy by leveraging early inverted latents for high harmonization and late latents for semantic consistency to generate a set of composite candidates. A lightweight harmony classifier is trained to further automatically select the most coherent result among them. We also construct RSIC-H, a benchmark dataset for satellite image harmonization derived from fMoW, providing 500 paired composition samples. Experiments demonstrate that our method effectively performs satellite image composition, showing strong potential for scalable remote-sensing synthesis and simulation tasks. Code is available at: https://github.com/XiaoqiZhuang/HarmoniDiff-RS.

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A straightforward solution is to employ a pseudo-labeling strategy, which is widely used in UDA to generate supervision for unlabeled target data, combined with an mm-3DPS backbone. However, existing supervised mm-3DPS methods rely heavily on strong cross-modal complementarity between LiDAR and RGB inputs, making them fragile under domain shifts where one modality degrades (e.g., poor lighting or adverse weather). Moreover, conventional pseudo-labeling typically retains only high-confidence regions, leading to fragmented masks and incomplete object supervision, which are issues particularly detrimental to panoptic segmentation. To address these challenges, we propose PanDA, the first UDA framework specifically designed for multimodal 3D panoptic segmentation. To improve robustness against single-sensor degradation, we introduce an asymmetric multimodal augmentation that selectively drops regions to simulate domain shifts and improve robust representation learning. To enhance pseudo-label completeness and reliability, we further develop a dual-expert pseudo-label refinement module that extracts domain-invariant priors from both 2D and 3D modalities. Extensive experiments across diverse domain shifts, spanning time, weather, location, and sensor variations, significantly surpass state-of-the-art UDA baselines for 3D semantic segmentation.

The emergence of sixth-generation (6G) technologies has introduced new challenges and opportunities for machine learning (ML) applications in Internet of Things (IoT) networks, particularly concerning energy efficiency. As model training and data transmission contribute significantly to energy consumption, optimizing these processes has become critical for sustainable system design. This study first conduct analysis on the energy consumption model for both centralized and decentralized architecture and then presents a testbed deployed within the German railway infrastructure, leveraging sensor data for ML-based predictive maintenance. A comparative analysis of distributed versus Centralized Learning (CL) architectures reveals that distributed models maintain competitive predictive accuracy (~90%) while reducing overall electricity consumption by up to 70%. These findings underscore the potential of distributed ML to improve energy efficiency in real-world IoT deployments, particularly by mitigating transmission-related energy costs.

Achieving truly fluid interaction with robots with speech interfaces remains a hard problem, and the experience of current Human-Robot Interaction (HRI) remains laboured and frustrating. Some of the barriers to fluid interaction stem from a lack of a suitable development platform for HRI for improving interaction, even in robotic Wizard-of-Oz (WoZ) modes of operation used for data collection and prototyping. Based on previous systems, we propose the properties of interruptibility and correction (IaC), pollability, latency measurement and optimisation and time-accurate reproducibility of actions from logging data as key criteria for a fluid WoZ system to support fluid error correction. We finish by presenting a Virtual Reality (VR) HRI simulation environment for mobile manipulators which meets these criteria.

Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these node representations remain opaque and difficult to interpret. Existing explainability methods primarily focus on supervised settings or on explaining individual representation dimensions, leaving a critical gap in explaining the overall structure of node representations. In this paper, we propose TACENR (Task-Agnostic Contrastive Explanations for Node Representations), a local explanation method that identifies not only attribute features but also proximity and structural ones that contribute the most in the representation space. TACENR builds on contrastive learning, through which we learn a similarity function in the representation space, revealing which are the features that play an important role in the representation of a node. While our focus is on task-agnostic explanations, TACENR can be applied to supervised scenarios as well. Experimental results demonstrate that proximity and structural features play a significant role in shaping node representations and that our supervised variant performs comparably to existing task-specific approaches in identifying the most impactful features.

Peak picking is a fundamental preprocessing step in Mass Spectrometry Imaging (MSI), where each sample is represented by hundreds to thousands of ion images. Existing approaches require careful dataset-specific hyperparameter tuning, and often fail to generalize across acquisition protocols. We introduce IonMorphNet, a spatial-structure-aware representation model for ion images that enables fully data-driven peak picking without any task-specific supervision. We curate 53 publicly available MSI datasets and define six structural classes capturing representative spatial patterns in ion images to train standard image backbones for structural pattern classification. Once trained, IonMorphNet can assess ion images and perform peak picking without additional hyperparameter tuning. Using a ConvNeXt V2-Tiny backbone, our approach improves peak picking performance by +7 % mSCF1 compared to state-of-the-art methods across multiple datasets. Beyond peak picking, we demonstrate that spatially informed channel reduction enables a 3D CNN for patch-based tumor classification in MSI. This approach matches or exceeds pixel-wise spectral classifiers by up to +7.3 % Balanced Accuracy on three tumor classification tasks, indicating meaningful ion image selection. The source code and model weights are available at https://github.com/CeMOS-IS/IonMorphNet.

Predicting driver intention from neurophysiological signals offers a promising pathway for enhancing proactive safety in advanced driver assistance systems, yet remains challenging in real-world driving due to EEG signal non-stationarity and the complexity of cognitive-motor preparation. This study proposes and evaluates an EEG-based driver intention prediction framework using a synchronised multi-sensor platform integrated into a real electric vehicle. A real-world on-road dataset was collected across 32 driving sessions, and 12 deep learning architectures were evaluated under consistent experimental conditions. Among the evaluated architectures, TSCeption achieved the highest average accuracy (0.907) and Macro-F1 score (0.901). The proposed framework demonstrates strong temporal stability, maintaining robust decoding performance up to 1000 ms before manoeuvre execution with minimal degradation. Furthermore, additional analyses reveal that minimal EEG preprocessing outperforms artefact-handling pipelines, and prediction performance peaks within a 400-600 ms interval, corresponding to a critical neural preparatory phase preceding driving manoeuvres. Overall, these findings support the feasibility of early and stable EEG-based driver intention decoding under real-world on-road conditions. Code: https://github.com/galosaimi/Mind2Drive.

Face recognition systems are often used for biometric authentication. Nevertheless, it is known that without any protective measures, face recognition systems are vulnerable to presentation attacks. To tackle this security problem, methods for detecting presentation attacks have been developed and shown good detection performance on several benchmark datasets. However, generalising presentation attack detection methods to new and novel types of attacks is an ongoing challenge. In this work, we employ 1,608 T-shirt attacks of the T-shirt Face Presentation Attack (TFPA) database using 100 unique presentation attack instruments together with 152 bona fide presentations. In a comprehensive evaluation, we show that this type of attack can compromise the security of face recognition systems. Furthermore, we propose a detection method based on spatial consistency checks in order to detect said T-shirt attacks. Precisely, state-of-the-art face and person detectors are combined to analyse the spatial positions of detected faces and persons based on which T-shirt attacks can be reliably detected.

The evaluation of machine learning models typically relies mainly on performance metrics based on loss functions, which risk to overlook changes in performance in relevant subgroups. Auditing tools such as SliceFinder and SliceLine were proposed to detect such groups, but usually have conceptual disadvantages, such as the inability to directly address continuous covariates. In this paper, we introduce FairTree, a novel algorithm adapted from psychometric invariance testing. Unlike SliceFinder and related algorithms, FairTree directly handles continuous, categorical, and ordinal features without discretization. It further decomposes performance disparities into systematic bias and variance, allowing a categorization of changes in algorithm performance. We propose and evaluate two variations of the algorithm: a permutation-based approach, which is conceptually closer to SliceFinder, and a fluctuation test. Through simulation studies that include a direct comparison with SliceLine, we demonstrate that both approaches have a satisfactory rate of false-positive results, but that the fluctuation approach has relatively higher power. We further illustrate the method on the UCI Adult Census dataset. The proposed algorithms provide a flexible framework for the statistical evaluation of the performance and aspects of fairness of machine learning models in a wide range of applications even in relatively small data.

Large Language Model (LLM) agents are increasingly proposed for autonomous cybersecurity tasks, but their capabilities in realistic offensive settings remain poorly understood. We present DeepRed, an open-source benchmark for evaluating LLM-based agents on realistic Capture The Flag (CTF) challenges in isolated virtualized environments. DeepRed places an agent in a Kali attacker environment with terminal tools and optional web search, connected over a private network to a target challenge, and records full execution traces for analysis. To move beyond binary solved/unsolved outcomes, we introduce a partial-credit scoring method based on challenge-specific checkpoints derived from public writeups, together with an automated summarise-then-judge labelling pipeline for assigning checkpoint completion from logs. Using DeepRed, we benchmark ten commercially accessible LLMs on ten VM-based CTF challenges spanning different challenge categories. The results indicate that current agents remain limited: the best model achieves only 35% average checkpoint completion, performing strongest on common challenge types and weakest on tasks requiring non-standard discovery and longer-horizon adaptation.

Vision Transformers $(\texttt{ViT})$ have become the architecture of choice for many computer vision tasks, yet their performance in computer-aided diagnostics remains limited. Focusing on breast cancer detection from mammograms, we identify two main causes for this shortfall. First, medical images are high-resolution with small abnormalities, leading to an excessive number of tokens and making it difficult for the softmax-based attention to localize and attend to relevant regions. Second, medical image classification is inherently fine-grained, with low inter-class and high intra-class variability, where standard cross-entropy training is insufficient. To overcome these challenges, we propose a framework with three key components: (1) Region of interest $(\texttt{RoI})$ based token reduction using an object detection model to guide attention; (2) contrastive learning between selected $\texttt{RoI}$ to enhance fine-grained discrimination through hard-negative based training; and (3) a $\texttt{DINOv2}$ pretrained $\texttt{ViT}$ that captures localization-aware, fine-grained features instead of global $\texttt{CLIP}$ representations. Experiments on public mammography datasets demonstrate that our method achieves superior performance over existing baselines, establishing its effectiveness and potential clinical utility for large-scale breast cancer screening. Our code is available for reproducibility here: https://aih-iitd.github.io/publications/attend-what-matters

Monocular scene flow estimation aims to recover dense 3D motion from image sequences, yet most existing methods are limited to two-frame inputs, restricting temporal modeling and robustness to occlusions. We propose RAFT-MSF++, a self-supervised multi-frame framework that recurrently fuses temporal features to jointly estimate depth and scene flow. Central to our approach is the Geometry-Motion Feature (GMF), which compactly encodes coupled motion and geometry cues and is iteratively updated for effective temporal reasoning. To ensure the robustness of this temporal fusion against occlusions, we incorporate relative positional attention to inject spatial priors and an occlusion regularization module to propagate reliable motion from visible regions. These components enable the GMF to effectively propagate information even in ambiguous areas. Extensive experiments show that RAFT-MSF++ achieves 24.14% SF-all on the KITTI Scene Flow benchmark, with a 30.99% improvement over the baseline and better robustness in occluded regions. The code is available at https://github.com/sunzunyi/RAFT-MSF-PlusPlus.

This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the ultra-fine-grained visual categorization (Ultra-FGVC) task in data-limited scenarios. Unlike prior work that often captures subtle yet critical distinctions, GAEor generates geometric attributes as novel alternative recognition cues. These attributes are determined by various details within the object, aligned with its geometric patterns, such as the intricate vein structures in soybean leaves. Crucially, each category exhibits distinct geometric descriptors that serve as powerful cues, even among objects with minimal visual variation -- a factor largely overlooked in recent research. GAEor discovers these geometric attributes by first amplifying geometry-relevant details via visual feedback from a backbone network, then embedding the relative polar coordinates of these details into the final representation. Extensive experiments demonstrate that GAEor significantly sets new state-of-the-art records in five widely-used Ultra-FGVC benchmarks.

Robotic parkour provides a compelling benchmark for advancing locomotion over highly challenging terrain, including large discontinuities such as elevated steps. Recent approaches have demonstrated impressive capabilities, including dynamic climbing and jumping, but typically rely on sequential multilayer perceptron (MLP) architectures with densely activated layers. In contrast, sparsely gated mixture-of-experts (MoE) architectures have emerged in the large language model domain as an effective paradigm for improving scalability and performance by activating only a subset of parameters at inference time. In this work, we investigate the application of sparsely gated MoE architectures to vision-based robotic parkour. We compare control policies based on standard MLPs and MoE architectures under a controlled setting where the number of active parameters at inference time is matched. Experimental results on a real Unitree Go2 quadruped robot demonstrate clear performance gains, with the MoE policy achieving double the number of successful trials in traversing large obstacles compared to a standard MLP baseline. We further show that achieving comparable performance with a standard MLP requires scaling its parameter count to match that of the total MoE model, resulting in a 14.3\% increase in computation time. These results highlight that sparsely gated MoE architectures provide a favorable trade-off between performance and computational efficiency, enabling improved scaling of control policies for vision-based robotic parkour. An anonymized link to the codebase is https://osf.io/v2kqj/files/github?view_only=7977dee10c0a44769184498eaba72e44.

Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost control are critical. In such settings, models must satisfy strict constraints on energy, latency, and hardware utilization-not accuracy alone. Yet prevailing evaluation pipelines remain accuracy-centric, creating a Deployment-Evaluation Gap-the absence of operational and economic criteria in model assessment. To address this gap, we present EDGE-EVAL-a industry-oriented benchmarking framework that evaluates LLMs across their full lifecycle on legacy NVIDIA Tesla T4 GPUs. Benchmarking LLaMA and Qwen variants across three industrial tasks, we introduce five deployment metrics-Economic Break-Even (Nbreak), Intelligence-Per-Watt (IPW ), System Density (\r{ho}sys), Cold-Start Tax (Ctax), and Quantization Fidelity (Qret)-capturing profitability, energy efficiency, hardware scaling, serverless feasibility, and compression safety. Our results reveal a clear efficiency frontier-models in the <2B parameter class dominate larger baselines across economic and ecological dimensions. LLaMA-3.2-1B (INT4) achieves ROI break-even in 14 requests (median), delivers 3x higher energy-normalized intelligence than 7B models, and exceeds 6,900 tokens/s/GB under 4-bit quantization. We further uncover an efficiency anomaly-while QLoRA reduces memory footprint, it increases adaptation energy by up to 7x for small models-challenging prevailing assumptions about quantization-aware training in edge deployment.

Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of obtaining feedback on candidate solutions via verifiers, simulators, or task-specific scoring functions. While prior work has highlighted the importance of evaluation, it has not explicitly formulated the problem of how evaluation-driven discovery loops can be scaled up in a principled and effective manner to push the boundaries of scientific discovery, a problem this paper seeks to address. We introduce Simple Test-time Evaluation-driven Scaling (SimpleTES), a general framework that strategically combines parallel exploration, feedback-driven refinement, and local selection, revealing substantial gains unlocked by scaling evaluation-driven discovery loops along the right dimensions. Across 21 scientific problems spanning six domains, SimpleTES discovers state-of-the-art solutions using gpt-oss models, consistently outperforming both frontier-model baselines and sophisticated optimization pipelines. Particularly, we sped up the widely used LASSO algorithm by over 2x, designed quantum circuit routing policies that reduce gate overhead by 24.5%, and discovered new Erdos minimum overlap constructions that surpass the best-known results. Beyond novel discoveries, SimpleTES produces trajectory-level histories that naturally supervise feedback-driven learning. When post-trained on successful trajectories, models not only improve efficiency on seen problems but also generalize to unseen problems, discovering solutions that base models fail to uncover. Together, our results establish effective evaluation-driven loop scaling as a central axis for advancing LLM-driven scientific discovery, and provide a simple yet practical framework for realizing these gains.

Ultra-fine-grained visual categorization (Ultra-FGVC) aims to classify highly similar subcategories within fine-grained objects using limited training samples. However, holistic yet discriminative cues, such as leaf contours in extremely similar cultivars, remain under-explored in current studies, thereby limiting recognition performance. Though crucial, modeling holistic cues with complex morphological structures typically requires massive training samples, posing significant challenges in data-limited scenarios. To address this challenge, we propose a novel Divide-and-Conquer Holistic Cognition Network (DHCNet) that implements a divide-and-conquer strategy by decomposing holistic cues into spatially-associated subtle discrepancies and progressively establishing the holistic cognition process, significantly simplifying holistic cognition while reducing dependency on training data. Technically, DHCNet begins by progressively analyzing subtle discrepancies, transitioning from smaller local patches to larger ones using a self-shuffling operation on local regions. Simultaneously, it leverages the unaffected local regions to potentially guide the perception of the original topological structure among the shuffled patches, thereby aiding in the establishment of spatial associations for these discrepancies. Additionally, DHCNet incorporates the online refinement of these holistic cues discovered from local regions into the training process to iteratively improve their quality. As a result, DHCNet uses these holistic cues as supervisory signals to fine-tune the parameters of the recognition model, thus improving its sensitivity to holistic cues across the entire objects. Extensive evaluations demonstrate that DHCNet achieves remarkable performance on five widely-used Ultra-FGVC datasets.

Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate information through an explicit recurrent state. These mechanisms face different limitations on long contexts: when attention is diffuse, the influence of individual tokens is diluted across the effective support, while recurrent state propagation can lose long-range sensitivity unless information is actively preserved. As a result, both mechanisms face challenges in preserving and selectively retrieving information over long contexts. We propose Sessa, a decoder that places attention inside a recurrent feedback path. This creates many attention-based paths through which past tokens can influence future states, rather than relying on a single attention read or a single recurrent chain. We prove that, under explicit assumptions and matched regimes, Sessa admits power-law memory tails $O(\ell^{-β})$ for $0 < β< 1$, with slower decay than in the corresponding Transformer and Mamba-style baselines. We further give an explicit construction that achieves this power-law rate. Under the same assumptions, Sessa is the only model class among those considered that realizes flexible selective retrieval, including profiles whose influence does not decay with distance. Consistent with this theoretical advantage, across matched experiments, Sessa achieves the strongest performance on long-context benchmarks while remaining competitive with Transformer and Mamba-style baselines on short-context language modeling.

We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is built on three ideas. (1) A linguistic belief state: a semi-structured representation combining numerical probability estimates with natural-language evidence summaries, updated by the LLM at each step of an iterative tool-use loop. This contrasts with the common approach of appending all retrieved evidence to an ever-growing context. (2) Hierarchical multi-trial aggregation: running $K$ independent trials and combining them using logit-space shrinkage with a data-dependent prior. (3) Hierarchical calibration: Platt scaling with a hierarchical prior, which avoids over-shrinking extreme predictions for sources with skewed base rates. On 400 backtesting questions from the ForecastBench leaderboard, BLF outperforms all the top public methods, including Cassi, GPT-5, Grok~4.20, and Foresight-32B. Ablation studies show that the structured belief state is almost as impactful as web search access, and that shrinkage aggregation and hierarchical calibration each provide significant additional gains. In addition, we develop a robust back-testing framework with a leakage rate below 1.5\%, and use rigorous statistical methodology to compare different methods while controlling for various sources of noise.

Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in multi-agent coordination, and limited generalization across objects. In this paper, we present SynAgent, a unified framework that enables scalable and physically plausible cooperative manipulation by leveraging Solo-to-Cooperative Agent Synergy to transfer skills from single-agent human-object interaction to multi-agent human-object-human scenarios. To maintain semantic integrity during motion transfer, we introduce an interaction-preserving retargeting method based on an Interact Mesh constructed via Delaunay tetrahedralization, which faithfully maintains spatial relationships among humans and objects. Building upon this refined data, we propose a single-agent pretraining and adaptation paradigm that bootstraps synergistic collaborative behaviors from abundant single-human data through decentralized training and multi-agent PPO. Finally, we develop a trajectory-conditioned generative policy using a conditional VAE, trained via multi-teacher distillation from motion imitation priors to achieve stable and controllable object-level trajectory execution. Extensive experiments demonstrate that SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control, while generalizing across diverse object geometries. Codes and data will be available after publication. Project Page: http://yw0208.github.io/synagent