arXiv:2505.07579v2 Announce Type: replace
Abstract: We study \emph{rental games} -- a single-parameter dynamic mechanism design problem, in which a designer rents out an indivisible asset over $n$ days. Each day, an agent arrives with a private valuation per day of rental, drawn from that day's (known) distribution. The designer can either rent out the asset to the current agent for any number of remaining days, charging them a (possibly different) payment per day, or turn the agent away. Agents who arrive when the asset is not available are turned away. A defining feature of our dynamic model is that agents are \emph{stagewise-IR} (individually rational), meaning they reject any rental agreement that results in temporary negative utility, even if their final utility is positive. We ask whether and under which economic objectives it is useful for the designer to exploit the stagewise-IR nature of the agents.
We show that an optimal rental mechanism can be modeled as a sequence of dynamic auctions with seller costs. However, the stagewise-IR behavior of the agents makes these auctions quite different from classical single-parameter auctions: Myerson's Lemma does not apply, and indeed we show that truthful mechanisms are not necessarily monotone, and payments do not necessarily follow Myerson's unique payment rule. We develop alternative characterizations of optimal mechanisms under several classes of economic objectives, including generalizations of welfare, revenue and consumer surplus. These characterizations allow us to use Myerson's unique payment rule in several cases, and for the other cases we develop optimal mechanisms from scratch. Our work shows that rental games raise interesting questions even in the single-parameter regime.
Science Journals
arXiv:2505.09433v3 Announce Type: replace
Abstract: Reflectance attributes in LiDAR point clouds provide essential information for downstream tasks but remain underexplored in neural compression methods. To address this, we introduce SerLiC, a serialization-based neural compression framework to fully exploit the intrinsic characteristics of LiDAR reflectance. SerLiC first transforms 3D LiDAR point clouds into 1D sequences via scan-order serialization, offering a device-centric perspective for reflectance analysis. Each point is then tokenized into a contextual representation comprising its sensor scanning index, radial distance, and prior reflectance, for effective dependencies exploration. For efficient sequential modeling, Mamba is incorporated with a dual parallelization scheme, enabling simultaneous autoregressive dependency capture and fast processing. Extensive experiments demonstrate that SerLiC attains over 2x volume reduction against the original reflectance data, outperforming the state-of-the-art method by up to 22% reduction of compressed bits while using only 2% of its parameters. Moreover, a lightweight version of SerLiC achieves > 10 fps (frames per second) with just 111K parameters, which is attractive for real-world applications.
arXiv:2607.13117v1 Announce Type: new
Abstract: We introduce a graded graph-series semantics for recursive hybrid quantum
programs interpreted in the quantum orchestra monad. Finite terminating
executions are represented by directed paths whose edges carry normal
completely positive subunital maps and whose terminal vertices carry classical
results. Path concatenation defines a graded execution category, while
continuation grafting models outcome-dependent sequential composition. We
construct a semantic evaluation from admissible execution-graph series to
quantum orchestras and prove that it is compatible with both channel
composition and Kleisli composition.
For finitary recursive programs, the truncation of the execution series at
degree $n$ is shown to coincide with the $n$-th Kleene approximant of the
associated Scott-continuous recursion functional. Consequently, evaluation of
the complete graph series recovers the ordinary least-fixed-point denotation.
Weighting a graph of degree $n$ by $q^n$, with $0<q<1$, yields an
Abel-regularised semantics whose Scott limit as $q\to 1^{-}$ is the
unregularised recursive denotation. Equivalently, the parametrisation
$q=e^{-t}$ exponentially suppresses long executions and reconstructs the
denotation as $t\to 0^{+}$.
In a supplementary linear feedback sector, repeated recursion is represented
by the execution resolvent $(I-qST)^{-1}$. We identify $I-qST$ with an
algebraic cross-ratio of graph subspaces. Under Hilbert--Schmidt assumptions,
the associated return operator is trace class and defines the Fredholm
feedback determinant
\(
\operatorname{det}_{F}(I-qST),
\)
whose zeros detect singular feedback configurations and whose logarithmic
expansion records closed loop traversals.
arXiv:2506.15124v2 Announce Type: replace
Abstract: This paper presents the design, modeling, and control of a dual-bearing magnetorheological grease (MRG) clutch for wearable haptic feedback. Compared with conventional MR fluid devices, the proposed clutch avoids leakage-related reliability degradation while achieving high torque density in a compact structure. To provide physical insight into the torque-generation mechanism, a physics-inspired interpretive model is introduced to capture the dominant relationship among excitation current, magnetic-field evolution in the bearing gaps, and clutch locking torque. To mitigate the undesirable ``sticky'' sensation caused by passive bidirectional braking, an intention-based control strategy with active demagnetization is further developed to enable smoother release during human--robot interaction. Experimental characterization shows that the proposed clutch achieves a maximum locking torque of 43.42\,N$\cdot$m at 1.3\,A and a torque-to-mass ratio of 96.5\,N$\cdot$m/kg. Bench tests, replay validation, teleoperation experiments, and user studies indicate that the proposed approach accelerates clutch release and improves perceived release transparency and contact-to-release smoothness, while maintaining effective multi-level kinesthetic rendering.
arXiv:2607.13595v1 Announce Type: new
Abstract: Integrating mobile robots into human teams promises significant capability improvements for tasks such as searching hazardous environments. Unlike existing teleoperated robots, future robot systems will increasingly be endowed with some level of artificial intelligence (AI), giving them a degree of autonomy in how they pursue mission goals. This autonomy could make a human-agent (robot) team more effective but also put inter-agent trust under strain if robots make a mistake, or (appear to) pursue task priorities that conflict with the team's best interest. During a mission, agents' trust states are anticipated to vary according to the situation as understood by each teammate (trustor). If component-level (agent) or system-level trust falls below sufficient levels for cooperative tasks to be completed, it could critically affect mission success . We argue that active trust management will be an important precondition for the success of human-robot teams (HRTs, a subcategory of human-agent teams with embodied agents), especially in dynamic, high-risk environments. We present a trust satisficing perspective which acknowledges and attempts to account for the fluctuating, multi-faceted, and context-dependent nature of trust and trust requirements even under normal operating conditions. Our outline of a trust management framework for human-robot teaming includes online measurement of proxy metrics for trust, closed-loop adaptation of robot behavior, and variable autonomy to give space for human responsibility in situations requiring value judgements. We refer to a recent experimental exploration of 'swift trust' and a novel behavioral trust metric for HRT, and we highlight issues for further investigation.
arXiv:2607.13160v1 Announce Type: new
Abstract: Active beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) enables hybrid transmitting and reflecting mode to achieve effective signal amplification and full-space coverage, thus providing a promising solution for blockage-aware uplink offloading in heterogeneous mobile edge computing (MEC) systems. However, practical hybrid mode active BD-RIS are realized by reciprocal devices, which inherently generate cross-sector energy leakage that will reshape the system-level energy-latency tradeoff. This paper studies energy-aware offloading and resource allocation for reciprocal active BD-RIS-assisted heterogeneous MEC, where offloading decisions, CPU/GPU computation allocation, transmit powers, receive processing, and active BD-RIS are tightly coupled. The resulting problem is a high-dimensional mixed integer nonconvex problem and is difficult to solve efficiently by conventional per-instance optimization. To address this challenge, we develop an end-to-end joint optimization framework based on a refined version of the distributional soft actor--critic algorithm, named as DSAC-T. By modeling return distributions rather than only expected values, DSAC-T improves policy stability under reward heterogeneity and feasibility-boundary sensitivity. Compared with other baseline algorithms, DSAC-T achieves the best energy-latency reward, the highest feasibility ratio of 81.67%, and a fast online decision time of 0.0267 s per scenario.
arXiv:2607.13298v1 Announce Type: new
Abstract: In online streaming video understanding, a video stream continues to arrive and queries may be issued at any time. Because streaming frames grow without bound, the system must continuously compress and retain information from the observed video prefix while future frames and future queries remain unknown. The core challenge is deciding what information to retain and how to organize the maintained history: as this history grows with the stream, memory cost increases and many redundant visual details are retained, whereas later queries often depend on specific entities, actions, and their temporal changes. To address this challenge, we introduce FOLIO, a training-free focused semantic memory system that records important parts of the stream in higher detail while keeping surrounding context compact. As the stream arrives, FOLIO updates memory at the segment level, guided by a dynamic focus state, combining a short-term visual buffer with a long-term semantic memory organized around observed entities and linked to a visual-evidence cache. At query time, lightweight hybrid retrieval combines direct matching over the structured memory with semantic query expansion. FOLIO achieves state-of-the-art performance, reaching 82.0/69.1 Perception/Backward accuracy on OVO-Bench with Qwen3-VL-8B and 74.5 overall accuracy on StreamingBench, while substantially reducing the cost of maintaining streaming memory by reserving detailed records for focused entities and storing surrounding context compactly.
arXiv:2507.01224v2 Announce Type: replace
Abstract: Scientific simulation leveraging high-performance computing (HPC) systems is crucial for modeling complex systems and phenomena in fields such as astrophysics, climate science, and fluid dynamics, generating massive datasets that often reach petabyte to exabyte scales. However, managing these vast data volumes introduces significant I/O and network bottlenecks, limiting practical performance and scalability. While cutting-edge lossy compression frameworks powered by deep neural networks (DNNs) have demonstrated superior compression ratios by capturing complex data correlations, their integration into HPC workflows poses substantial challenges due to the hybrid non-neural and neural computation patterns, causing excessive memory access overhead, large sequential stalls, and limited adaptability to varying data sizes and workloads in existing hardware platforms. To overcome these challenges and push the limit of high-performance scientific computing, we for the first time propose FLARE, a dataflow-aware and scalable hardware architecture for neural-hybrid scientific lossy compression. FLARE minimizes off-chip data access, reduces bubble overhead through efficient dataflow, and adopts a modular design that provides both scalability and flexibility, significantly enhancing throughput and energy efficiency on modern HPC systems. Particularly, the proposed FLARE achieves runtime speedups ranging from $3.50 \times$ to $96.07 \times$, and energy efficiency improvements ranging from $24.51 \times$ to $520.68 \times$, across various datasets and hardware platforms.
arXiv:2507.16849v3 Announce Type: replace
Abstract: We propose a vision transformer (ViT)-based deep learning framework to refine disaster-affected area segmentation from remote sensing imagery, aiming to support and enhance the Emergent Value Added Product (EVAP) developed by the Taiwan Space Agency (TASA). The process starts with a small set of manually annotated regions. We then apply principal component analysis (PCA)-based feature space analysis and construct a confidence index (CI) to expand these labels, producing a weakly supervised training set. These expanded labels are then used to train ViT-based encoder-decoder models with multi-band inputs from Sentinel-2 and Formosat-5 imagery. Our architecture supports multiple decoder variants and multi-stage loss strategies to improve performance under limited supervision. During the evaluation, model predictions are compared with higher-resolution EVAP output to assess spatial coherence and segmentation consistency. Case studies on the 2022 Poyang Lake drought and the 2023 Rhodes wildfire demonstrate that our framework improves the smoothness and reliability of segmentation results, offering a scalable approach for disaster mapping when accurate ground truth is unavailable.
arXiv:2607.13323v1 Announce Type: new
Abstract: The Segment Anything Model (SAM) has demonstrated strong generalizability across a variety of segmentation tasks. However, SAM often struggles in situations where the target to be segmented is ambiguous. This poses a problem in medical imaging, where accurate delineation of targets such as tumors is vital, but even expert radiologists can disagree on the appropriate boundary for a target. Addressing this, we propose SARFA (Segment Anything with Radiomic Feature Alignment), a novel framework for improved medical image segmentation. Via probabilistic prompting, SARFA generates a diverse set of plausible masks for each input image and optimizes them with a radiomics-driven training objective based on Fr\'echet Radiomic Distance (FRD) and Direct Preference Optimization (DPO). By minimizing the FRD between masked predicted and ground truth regions within each image, SARFA encourages segmentation outputs whose anatomical and textural characteristics align with clinically meaningful ground truth representations, without relying solely on pixel-level overlap. Evaluated on computed tomography (CT) and magnetic resonance imaging (MRI) benchmarks, SARFA outperforms existing ambiguous segmentation methods, demonstrating the effectiveness of radiomic feature alignment and DPO-style candidate mask ranking as a training objective. Our code is available at https://github.com/tbwa233/SARFA.
arXiv:2607.13496v1 Announce Type: new
Abstract: Turbulent boundary layers characterised by friction Reynolds numbers in the range $Re_{\tau} = 880 - 1460$ and flowing over flush-mounted passively rotating discs are investigated in a wind tunnel with the purpose of reducing the skin-friction drag. The test surface is composed of thirty-two rotating discs arranged in a staggered configuration and supported by bearings mounted in cylindrical cavities. As the discs are half covered by thin rigid plates, a steady rotation of the discs is sustained via the asymmetric distribution of the wall-shear stress exerted by the wall turbulence on the exposed halves of the discs. Direct force measurements reveal that the drag increases with respect to a flat-plate case because of the flow interaction with the disc housings and the covering plates. The effect of the disc motion is isolated and a 3\% drag reduction is measured with respect to the flow over stationary discs. The skin-friction identity by \cite{Elnahhas_Johnson_2022} (\emph{J. Fluid Mech.}, vol. 940, 2022), extended herein to include the disc-flow effects, is utilised for the first time to analyse experimental data. This direct slip effect, quantified by using the measured disc angular velocities in the Elnahhas-Johnson identity, is negligible. Measurements obtained by particle image velocimetry disclose that a roughness mean-flow effect occurs between adjacent discs because of the clearance gaps around the discs and that a downwash secondary flow exists near the covering plates, analogous to flows over streamwise-elongated rectangular roughness elements. This downwash velocity is streamwise modulated because of the spanwise disc motion and alters the wall-normal transport term in the Elnahhas-Johnson identity, thus reducing the drag locally.
arXiv:2607.13504v1 Announce Type: new
Abstract: On-the-fly category discovery requires deciding for each incoming test sample whether to assign it to an existing category or spawn a new one. Existing methods typically implement this decision through matching-based heuristics, such as radius- or hash-based rules. While effective in practice, these methods usually treat category birth implicitly as a fallback when no existing category matches confidently, rather than as an explicit alternative supported by its own statistical evidence. To address this, we propose DP-BOA, a posterior-predictive decision framework based on an online Dirichlet-process Gaussian mixture model with a Normal-Inverse-Wishart prior. During training, we use labeled data to calibrate a shared NIW prior over category Gaussians and warm-start the known-category posteriors. At test time, for each incoming sample, DP-BOA compares the posterior predictive evidence for assignment to existing categories against the evidence for spawning a new category induced by the DP prior, and then updates category statistics online after the decision. The method captures anisotropic category geometry and naturally adapts decision confidence as evidence accumulates. Across standard OCD benchmarks, DP-BOA consistently outperforms strong baselines and delivers particularly strong novel-class discovery performance while maintaining competitive known-class accuracy.
arXiv:2607.13509v1 Announce Type: new
Abstract: In this paper, we develop a novel multi-frequency factorization method to reconstruct the spatial support of the ambient noise source. The proposed method only requires sparse correlation data and has low computational cost. Numerical experiments in two and three dimensions are presented to demonstrate the effectiveness of the proposed method.
arXiv:2507.19593v3 Announce Type: replace
Abstract: Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often violated in real-world MAS characterized by uncertainty, misaligned perceptions, and nested beliefs. To overcome these limitations, researchers have proposed extensions that incorporate models of cognitive constraints, subjective beliefs, and heterogeneous reasoning. Among these, hypergame theory extends the classical paradigm by explicitly modeling agents' subjective perceptions of the strategic scenario, known as perceptual games, in which agents may hold divergent beliefs about the structure, payoffs, or available actions. We present a systematic review of agent-compatible applications of hypergame theory, examining how its descriptive capabilities have been adapted to dynamic and interactive MAS contexts. We analyze 49 selected studies from cybersecurity, robotics, social simulation, communications, and general game-theoretic modeling. Building on a formal introduction to hypergame theory and its two major extensions - hierarchical hypergames and HNF - we develop agent-compatibility criteria and an agent-based classification framework to assess integration patterns and practical applicability. Our analysis reveals prevailing tendencies, including the prevalence of hierarchical and graph-based models in deceptive reasoning and the simplification of extensive theoretical frameworks in practical applications. We identify structural gaps, including the limited adoption of HNF-based models, the lack of formal hypergame languages, and unexplored opportunities for modeling human-agent and agent-agent misalignment. By synthesizing trends, challenges, and open research directions, this review provides a new roadmap for applying hypergame theory to enhance the realism and effectiveness of strategic modeling in dynamic multi-agent environments.
arXiv:2507.23270v3 Announce Type: replace
Abstract: Reconfigurable multi-robot cells offer a promising approach to meet fluctuating assembly demands. However, the recurrent planning of their configurations introduces new challenges, particularly in generating optimized, coordinated multi-robot motion sequences that minimize the assembly duration. This work presents a simulation-based method for generating such optimized sequences. The approach separates assembly steps into task-related core operations and connecting traverse operations. While core operations are constrained and predetermined, traverse operations offer substantial optimization potential. Scheduling the core operations is formulated as an optimization problem, requiring feasible traverse operations to be integrated using a decomposition-based motion planning strategy. Several solution techniques are explored, including a sampling heuristic, tree-based search and gradient-free optimization. For motion planning, a decomposition method is proposed that identifies specific areas in the schedule, which can be solved independently with modified centralized path planning algorithms. The proposed method generates efficient and collision-free multi-robot assembly procedures that outperform a baseline relying on decentralized, robot-individual motion planning. Its effectiveness is demonstrated through simulation experiments.
arXiv:2508.10671v3 Announce Type: replace
Abstract: The selection of a balanced active space is a critical step in multi-reference quantum chemistry calculations, particularly for systems with strong electron correlation. Likewise, active space selection is a key to unlock the potential of contemporary quantum computing in quantum chemistry. Albeit recent progress, there remains a lack of a unified, robust, and fully automated framework for active space selection that performs reliably across a wide range of molecular systems.
In this work, we present a novel approach inspired by both the AVAS (Atomic Valence Active Space) and AutoCAS methods. Our method unifies orbital entropy analysis with atomic orbital projections to guide the construction of chemically and physically meaningful active spaces. This integrated scheme enables a more consistent and flexible selection of active orbitals while retaining automation and scalability. We validate our approach on a set of molecular systems relevant to photodynamic therapy, in particular a set of Ru(II)-complexes, selected to span increasing levels of electron correlation and structural complexity. These molecules serve as challenging test cases due to the presence of strong static correlation and the need for highly accurate electronic structure descriptions. Our results demonstrate that the method can reliably identify compact, chemically intuitive active spaces that capture the essential physics, making it suitable for both classical and quantum computational frameworks.
Furthermore, we have developed this approach in a package that is intuitive to use for users and can be interfaced with both standard quantum chemistry and quantum computing applications, making it accessible to a broad research community.
arXiv:2509.11076v2 Announce Type: replace
Abstract: The increasing size of large language models (LLMs) has led to a surge in memory requirements during training, often exceeding the capacity of high-bandwidth memory (HBM). Swap-based memory optimization incurs neither accuracy loss nor additional end-to-end overhead when effectively overlapped, thus being an attractive solution. However, existing swap methods assume consistent operator sequences, which is impractical in Eager Mode, where operator sequences can vary during change.
We propose Chameleon, which redesigns the end-to-end process of swap-based memory optimization and is the first work to consider varying operator sequences in Eager Mode. Chameleon (i) introduces a lightweight online profiler to enable continuous profiling for monitoring operator sequences, (ii) generates effective swap policies with limited operator information, and (iii) optimizes the policy execution module for accurate policy application and better performance. Experimental results demonstrate that Chameleon reduces profiling overhead by 84.25%, enables training models up to 4x larger than hardware memory while adapting to changes in operator sequences, improves performance by up to 38.94% compared to recomputation or high-degree parallelism.
arXiv:2509.22415v4 Announce Type: replace
Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect. Recent logit-lens attribution methods project each visual-token hidden state into the vocabulary space to explain generated words, but this token-wise readout introduces a mismatch: visual tokens are context-mixed by the model, while the attribution score is decoded independently at each token location. This often produces fragmented attribution maps and can be further affected by autoregressive context signals from preceding text tokens. We propose ERCR, an attribution framework built from Evidence Recomposition (ER) and Predictive Context Residualization (PCR). ER aggregates target evidence across multiple views with different token-to-region assignments, reducing attribution fragmentation caused by a single readout grid. PCR estimates a preceding-token context map with RBO-based rank relevance and subtracts its fitted component from the ER map to suppress context-token interference. Experiments on LLaVA, Qwen2-VL, and InternVL families across COCO Caption, GranDf, and OpenPSG show that ERCR improves visual evidence for target tokens and mitigates preceding-token context interference under the existing evaluation protocol. On Qwen2-VL-2B, ERCR improves TAM F1-IoU from 39.10 to 44.45 on COCO Caption and from 30.83 to 37.20 on GranDf. Overall, ERCR provides a practical refinement for token-level visual evidence inspection.
arXiv:2509.24563v3 Announce Type: replace
Abstract: Recent advances in video large language models (VideoLLMs) call for new evaluation protocols and benchmarks for video-language understanding. Inspired by the needle in a haystack test widely used by LLMs, we introduce a novel task of Needle in a Montage (NeMo), which is designed to assess the temporal understanding capabilities of advanced VideoLLMs. Specifically, the proposed task focuses on two fundamental abilities critical for temporal understanding, i.e., retrieval-style long-context recall and temporal grounding. To generate video question answering data for our task, we develop a scalable automated data generation pipeline that facilitates high-quality data synthesis. Built upon the proposed pipeline, we present NeMoBench, a video-language benchmark centered on our task. Specifically, our full set of NeMoBench features 31,378 automatically generated question-answer (QA) pairs from 13,486 videos with various durations ranging from seconds to hours. Experiments demonstrate that our pipeline can reliably and automatically generate high-quality evaluation data, enabling NeMoBench to be continuously updated with the latest videos. We evaluate 20 state-of-the-art models on our benchmark, providing extensive results and key insights into their capabilities and limitations. Our project page is available at: https://lavi-lab.github.io/NeMoBench.
arXiv:2510.13903v2 Announce Type: replace
Abstract: Chain-of-thought prompting has popularized step-by-step reasoning in large language models, yet model performance still degrades as problem complexity and context length grow. By decomposing difficult tasks with long contexts into shorter, manageable ones, recent multi-agent paradigms offer a promising near-term solution to this problem. However, the fundamental capacities of such systems are poorly understood. In this work, we propose a theoretical framework to analyze the expressivity of multi-agent systems. We apply our framework to three algorithmic families: state tracking, recall, and $k$-hop reasoning. We derive bounds on (i) the number of agents required to solve the task exactly, (ii) the quantity and structure of inter-agent communication, and (iii) the achievable speedups as problem size and context scale. Our results identify regimes where communication is provably beneficial, delineate tradeoffs between agent count and bandwidth, and expose intrinsic limitations when either resource is constrained. We complement our theoretical analysis with a set of experiments on pretrained LLMs using controlled synthetic benchmarks. Empirical outcomes confirm the tradeoffs between key quantities predicted by our theory. Collectively, our analysis offers principled guidance for designing scalable multi-agent reasoning systems.
arXiv:2510.14893v4 Announce Type: replace
Abstract: Autonomous high-speed navigation through large, complex environments requires real-time generation of agile trajectories that are dynamically feasible, collision-free, and satisfy state or actuator constraints. Modern trajectory planning techniques primarily use numerical optimization, as they enable the systematic computation of high-quality, expressive trajectories that satisfy various constraints. However, stringent requirements on computation time and the risk of numerical instability can limit the use of optimization-based planners in safety-critical scenarios. This work presents an optimization-free planning framework called STITCHER that stitches short trajectory segments together with graph search to compute long-range, expressive, and near-optimal trajectories in real-time. STITCHER outperforms modern optimization-based planners through our innovative planning architecture and several algorithmic developments that make real-time planning possible. Extensive simulation testing is performed to analyze the algorithmic components that make up STITCHER, along with a thorough comparison with three state-of-the-art optimization planners. Simulation tests show that safe trajectories can be created within a few milliseconds for paths that span the entirety of two 50 m x 50 m environments. Hardware tests with a custom quadrotor verify that STITCHER can produce trackable paths in real-time while respecting nonconvex constraints, such as limits on tilt angle and motor forces, with flight speeds up to 63 km/h.
arXiv:2510.15371v2 Announce Type: replace
Abstract: Classification of electroencephalogram (EEG) signals obtained during motor imagery (MI) has substantial application potential, including communication assistance and rehabilitation support for patients with motor impairments. These signals remain inherently susceptible to physiological artifacts (e.g., eye blinking and swallowing), which pose persistent challenges. Although Transformer-based approaches for classifying EEG signals have been widely adopted, they often struggle to capture fine-grained dependencies within them. To overcome these limitations, we propose Cortical-SSM, a novel architecture that extends deep state space models to capture integrated dependencies of EEG signals across temporal, spatial, and frequency domains. We validated our method across two large-scale public MI EEG datasets containing more than 50 subjects. Our method outperformed baseline methods on both benchmarks. Furthermore, visual explanations derived from our model indicate that it effectively captures neurophysiologically relevant regions of EEG signals. These results indicate that Cortical-SSM provides a robust and interpretable alternative to attention-based architectures for MI EEG decoding. By enabling physiologically grounded feature learning, our method advances the reliability of subject-independent EEG classification and supports the development of practical and clinically deployable brain-computer interface systems.
arXiv:2510.17868v3 Announce Type: replace
Abstract: Current coding benchmarks often inflate Large Language Model (LLM) capabilities due to static paradigms and data contamination, enabling models to exploit statistical shortcuts rather than genuine reasoning. To address this, we introduce UniCode, a generative evaluation framework that systematically probes LLM limits via: (1) multi-dimensional augmentation transforming seed problems into complex variations to disrupt fixed algorithmic patterns; (2) a highly reliable, automated test generation pipeline for scalable evaluation; and (3) fine-grained metrics for rich error signals. Experiments reveal a 31.2% performance collapse in state-of-the-art models on UniCode, primarily driven by deficiencies in conceptual modeling and scalability reasoning rather than syntactic errors. Furthermore, we uncover a seed-problem regression where models revert to memorized seed logic rather than following new specifications, signaling a reliance on shortcuts over reasoning. This work validates UniCode as a robust framework to expose model fragility and foster reasoning-oriented code intelligence.
arXiv:2510.24803v3 Announce Type: replace
Abstract: Inference-time search over multi-agent systems (MAS) wastes compute when it cannot identify which agent's intermediate message advanced progress. We present the Multi-Agent System Process Reward Model (MASPRM), which scores routed transcripts (ordered sequences of messages between agents) and acts as an inference controller for step-level beam search (SBS) and Monte Carlo Tree Search (MCTS). MASPRM is trained from multi-agent MCTS rollouts labeled only with terminal outcome rewards, without human step-level annotations. We evaluate on GSM8K, MATH, MMLU, and LogiQA. Under matched scorer size and comparable MCTS budget, MASPRM exceeds a size-matched ORM by $+2.0$ to $+3.0$ points at 1.5B and $+4.1$ to $+14.5$ at 7B across all four benchmarks, with additional scorer-scaling gains over policy likelihood at 7B (avg $+13.4$ under MCTS). MASPRM also improves ranking quality, reducing Hit@1 to Hit@5 gaps by up to $10.3$ points, with the largest gains under stepwise search that uses intermediate decisions. Code: https://github.com/milad1378yz/MASPRM
arXiv:2510.26707v2 Announce Type: replace
Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems. Therefore, studying the alignment of LLMs with human values has become a crucial field of inquiry. Prior work, however, mostly focuses on evaluating the alignment of fully trained models, overlooking the training dynamics by which models learn to express human values. In this work, we investigate how and at which stage value alignment arises during the course of a model's post-training. Our analysis disentangles the effects of post-training algorithms and datasets, measuring both the magnitude and time of value drifts during training. Experimenting with Llama-3 and Qwen-3 models of different sizes and popular supervised fine-tuning (SFT) and preference optimization datasets and algorithms, we find that the SFT phase generally establishes a model's values, and subsequent preference optimization rarely re-aligns these values. Furthermore, using a synthetic preference dataset that enables controlled manipulation of values, we find that different preference optimization algorithms lead to different value alignment outcomes, even when preference data is held constant. Our findings provide actionable insights into how values are learned during post-training and help to inform data curation, as well as the selection of models and algorithms for preference optimization to improve model alignment to human values.