Computation and Language
SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support
Ahnaf Atef Choudhury and Ramkrishna Saha
Medical large
language models are often judged by how many clinical questions they answer correctly. That view is useful, but it misses a practical risk. A model may know the right answer and still change its response when the same case is written in a different patient voice. This paper evaluates that risk as SDoH aware narrative anchoring bias. We use NarrativeShield SDoH MedQA, a counterfactual medical question answering
dataset in which each case appears in persona based narratives while the answer key remains fixed. The
dataset is reshaped from wide format into case grouped persona rows. We evaluate three open source instruction tuned LLMs from the Qwen2.5 family: 1.5B, 3B, and 7B. The final experiment uses 300 clinical cases and produces 8,100 model responses across three prompting conditions. We report persona level accuracy, counterfactual consistency, correct consistency, and narrative sensitivity error. Qwen2.5 7B achieves the best accuracy at 56.33 percent and the best correct consistency at 40.33 percent. Paired McNemar exact tests show significant accuracy gains for 7B over 3B in all
prompt settings. Even so, narrative sensitivity remains, with the lowest error still at 31.67 percent. These results suggest that trustworthy clinical decision support should be evaluated by both average correctness and stability across medically equivalent patient narratives.
Read the full abstract ▾
Robotics
Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation
Jianxiang Liu, Gaojing Zhang, Chuan Wen et al. (+4 more)
Ensuring reliability in uncertain environments remains difficult for long-horizon robotic manipulation. End-to-end VLA models are data-heavy and opaque, making diagnosis and verification difficult. Hierarchical pipelines are more interpretable, but their plans are often weakly grounded in observations, weakly aligned with low-level actions, and computed without online feedback, leading to open-loop behavior and
hallucinations. To address these issues, we introduce the Triplet-to-Track System (TTS), a closed-loop long-horizon imitation learning system that uses human
videos to reduce reliance on
robot-collected data. TTS represents high-level subgoals as instance-grounded triplets, translates them into continuous track priors for execution, and monitors task progress from observations for online replanning. Across diverse real-world long-horizon tasks, TTS achieves a 74.8% average success rate and supports object-level and compositional generalization.
Read the full abstract ▾
All authors Jianxiang Liu, Gaojing Zhang, Chuan Wen, Qipeng Liu, Yuxuan Zhao, Ning Guo, Wenzhao Lian
Robotics
Reproducible Vision-Guided 6-DoF Robotic Manipulator with a Mixed Stepper-Driver Architecture and Browser-Native Control
Lasan Perera, Deneth Priyadarshana, Dulana Pitiwaduge et al. (+2 more)
We present the NeuralNexus Arm, an open, low-cost 6-DOF robotic manipulator built by an undergraduate engineering team, together with the design decisions and debugging experience needed to reproduce it. The arm is driven by a single STM32H743 microcontroller on a custom printed
circuit board (PCB) and combines two stepper-driver strategies on one controller: push-pull 3.3 V step/direction outputs for onboard TMC2209 drivers on the three wrist joints, and open-drain outputs for external CL57T and DM542 drivers on the three high-torque proximal joints. We describe the mechanical design, mixed-driver electronics, interrupt-driven firmware, a MATLAB/Simscape-based inverse-kinematics pipeline, a browser-native control interface using the Web Serial API, and a lightweight
vision pipeline for object localisation and autonomous pick-and-place tasks. We also document non-obvious hardware and firmware failure modes encountered during the transition from a development board to the custom PCB as reproducibility guidance. All design files and firmware are released openly. The platform actuates all six axes under coordinated control at a 2 kHz update rate and executes both manual and pre-recorded motions from the browser interface.
Read the full abstract ▾
All authors Lasan Perera, Deneth Priyadarshana, Dulana Pitiwaduge, Isitha Dinujaya, Mokshan Colambage
Artificial Intelligence
Performance of a domain-specific large language model in answering patient questions in psychiatry
Alexander J. Hish, Arjun Nagendran and Scott N. Compton
Background This study was designed to evaluate whether a domain-specific large
language model (LLM) trained exclusively on patient education resources can answer questions about psychiatric medications, in a manner superior to LLM chatbots. We developed an LLM ("MIND") fine-tuned for clinical fidelity, trained on patient education resources from authoritative medical organizations. Methods We compared the responses of MIND, ChatGPT, and OpenEvidence to patient questions about escitalopram, using two methods: (1) computer analysis according to a rubric measuring accuracy, clarity, completeness, nuance, safety, and referral appropriateness; (2) ratings from N=10 board-licensed psychiatrists on similar metrics. Results When rated by rubric, MIND was rated highest in all domains (p<0.001). When rated by psychiatrists, ChatGPT was rated accurate more often than MIND with a negligible effect size (p=0.021, r=0.073); MIND was rated complete more often than ChatGPT with a small effect size (p<0.001, r=0.160); and MIND and ChatGPT were rated safe with the same frequency (p=0.955, r=0.002). The majority of psychiatrists preferred the responses generated by ChatGPT (57.6%) compared to MIND (42.4%, p=0.003). Conclusions MIND was able to answer many questions about escitalopram in a manner deemed accurate, complete, and safe by psychiatrists the majority of the time. However, despite MIND's ability to provide more complete responses, psychiatrists preferred ChatGPT's responses. MIND represents a step towards building safe LLM systems to enhance patient education in psychiatry.
Read the full abstract ▾
Sound · Cross-listed from eess.AS
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
Bingshen Mu, Xian Shi, Xiong Wang et al. (+6 more)
Multi-speaker automatic
speech recognition (MSASR) aims to jointly predict content transcriptions, speaker identities, and timestamps, thereby addressing the key question of "who spoke what and when" and holds substantial practical value in real-world multi-speaker scenarios. However, MSASR still encounters considerable challenges in the presence of fast turn transitions, overlapping
speech, and complex, diverse multi-speaker scenarios. In this work, we propose DiaScriber, an end-to-end multi-speaker diarization and transcription model built on a
speech large
language model. We first construct diverse data pipelines to cover a wide variety of multi-speaker scenarios and their complexities, including validation and refinement, turn-transition and overlapping-
speech simulation, and
multimodal annotation. Furthermore, DiaScriber is developed based on the pretrained version of Qwen3.5-Omni through a three-stage training strategy involving continual pretraining, supervised fine-tuning, and reinforcement learning. Experiments show that DiaScriber achieves superior performance over comparison methods across extensive multi-speaker scenario test sets and demonstrates outstanding generalization ability in unseen multi-speaker scenarios.
Read the full abstract ▾
All authors Bingshen Mu, Xian Shi, Xiong Wang, Zhifang Guo, Ting He, Xize Cheng, Yu Xi, Jin Xu, Lei Xie
Computer Vision
VersaDB: A High-Performance AI Storage Database for Unifying Mutimodal Datasets
Cong Wang, Zelin Liu, Yang Luo Ran Zhang et al. (+6 more)
The AI field has been rapidly developing, leading to the emergence of a large number of AI training
datasets of various types. These
datasets contain different modalities, including text, images, audio, etc., and may come in various data storage formats. With the advancement of AI hardware, AI computation units like GPUs, TPUs, and NPUs can greatly accelerate the training speed of AI models, which in turn increases the demand for faster data processing. When using existing AI processing frameworks to handle
datasets with different modalities and storage formats, processing speeds may be suboptimal due to issues such as data layout and the way users handle the data. Therefore, using a unified database to store multiple data formats can better manage and optimize data access. In this paper, we introduce VersaDB, a database designed specifically for AI
datasets with various modalities. We implemented a page-based storage system, separating structured and unstructured data. Additionally, we generated B+ tree-based index files to accelerate data access. VersaDB supports automatic sharding and maintains a hierarchical metadata management system, with corresponding metadata maintained at the page, shard, and global levels, forming the foundation for the efficient operation of the database. We also focused on ease of use by providing APIs for directly converting
datasets into VersaDB, as well as APIs for converting popular AI data storage formats (e.g., CSV, TFRecord, .bin) into VersaDB.Our experiments show that using VersaDB can achieve up to 5.35x acceleration and maintain consistent performance across different parallelism levels.
Read the full abstract ▾
All authors Cong Wang, Zelin Liu, Yang Luo Ran Zhang, Zhijian Guo, Hui Zhang, Fan Yu, Yanfei Cao, Naijie Gu, Jun Yu
Computation and Language
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
Wenhao Wu, Menghao Zhang, Xin Wang et al. (+3 more)
Reliable deployment of LLM
agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated trials, and recognizing when a request cannot, or cannot yet, be safely fulfilled. CAR-bench exposes this reliability gap in the domain of in-car assistants: an LLM-simulated user issues incomplete or ambiguous requests, requiring the
agent to resolve uncertainty through multi-turn dialogue and tool use while strictly adhering to domain policies. Even frontier models show a substantial gap between what they can solve at least once (Pass@3) and what they solve consistently across trials (Pass^k). We bridge this gap with TRACE (TRAjectory-Contrastive
Evolution), which iteratively improves a skill-based
agent's behavioral knowledge without modifying model weights. This knowledge is organized as a Skill Bank of modular, retrievable skills, each encoding a self-contained set of tool-use rules and behavioral guidelines. TRACE evolves this bank through an agentic self-
evolution loop: after each evaluation round, it groups trajectories by the skills invoked and refines each skill by contrasting successful and failed behaviors. The updated bank then guides subsequent rounds, while during deployment the Actor performs state-conditioned skill orchestration at every turn. On GPT-5.5, TRACE improves consistency (Pass^3) by 34.6 points, from 59.9% to 94.5%, while shrinking the gap between potential and reliable performance to just 4.0 points. On the official hidden set, TRACE achieved first place using GPT-5.6-Sol, attaining a Pass^3 score of 70%-a 40% relative improvement over the baseline. These results show that TRACE converts high model potential into stable, consistent performance gain. Project homepage: https://darwin-
agent.github.io/Car-bench-TRACE.
Read the full abstract ▾
All authors Wenhao Wu, Menghao Zhang, Xin Wang, Zhi Wang, Kun Shao, Jian Luan
Computer Vision
GuidedFlow: An Attention-Guided Framework for Anomaly Detection in Additive Manufacturing
Sosmita Paul and Krishna Roy
Additive Manufacturing (AM) plays a vital role in the ongoing industrial revolution. However, quality control remains crucial and challenging due to printing defects or potential cyber-physical intrusions. Image or
video-based anomaly detection is a key effort towards addressing these challenges. Various approaches have been explored in this domain, including reconstruction-based,
embedding-based, and flow-based methods. Though normalizing flow-based methods address some of the core challenges of unforeseen defects and generalization while maintaining detection performance, existing approaches struggle with tiny/stringing defects common in 3D printing. In a small-data setting, this poses a limitation in generalization. To address these limitations, we propose GuidedFlow, a novel
attention-guided normalizing flow model for anomaly detection and localization. GuidedFlow employs a pre-trained ResNet model, fine-tuned on the domain
dataset. An
attention-guided spatial and temporal flow framework models the dynamics across multiple scales and frames. A Spatio-Temporal
Attention Network (SAN) enables the flow model to prioritize relevant contextual cues from input frames. We evaluate GuidedFlow on our AM3D-AD
dataset, consisting of benign and anomalous real 3D printed object images and
videos. We also conduct a comparative study using the MVTec-AD industrial image anomaly detection
dataset. Experimental results demonstrate that GuidedFlow outperforms most of the state-of-the-art models with enhanced detection accuracy and AUROC.
Read the full abstract ▾
Artificial Intelligence
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang et al. (+15 more)
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy
distillation, and sampling-heavy evaluation. Unlike online serving, which typically targets request-level latency and throughput, synchronous rollouts must collect a complete batch before proceeding. A few long-tail generations can therefore dominate an entire rollout step, and uniform routing can slow these generations further by placing them in high-concurrency decoding batches. We present TailSieve, a partial-rollout-guided framework that jointly controls tail routing and replica allocation. Motivated by the observed persistence of
prompt-level tail tendencies across policy updates, TailSieve uses partial-rollout completion status as a training-free signal for identifying candidate tail groups. Selected
prompts are combined with newly sampled
prompts, and all responses are generated from scratch under the current policy. A hierarchical controller uses response-work history and a serving model: a fast inner loop adjusts the number of isolated groups to balance completion times, while a slower outer loop adapts how many replicas serve these groups. The resulting low-concurrency execution also enables route-specialized speculative decoding with MTP or DFlash. Across the evaluated configurations, TailSieve achieves up to $1.67\times$ speedup with routing alone and $2.59\times$ with routing and speculation combined, both over uniform group routing.
Read the full abstract ▾
All authors Tianqi Xu, Lu Lv, Haoyang Huang, Wenjie Huang, Zhanming Shen, Yuhao Shen, Baolin Zhang, Xinyi Hu, Shuang Ge, Jun Dai, Tianyu Liu, Suorong Yang, Zhikai Li, Ye Bai, Jun Zhang, Lei Chen, Yue Li, Mingchen Wan
Systems and Control
Generative Design of Liquid-Cooling Channels for Thermal Management of 2.5D and 3D Integrated Advanced Packaging
Michael Acquah and Zheng Liu
High-power multi-chip packages require increasingly effective cooling as intensive heat is generated within a limited package area. This work presents a physics-guided generative design framework for
liquid-cooling channel
topology optimization in a 2.7 kW multi-chip package containing two high-power graphics processing units (GPUs) and one central processing unit (CPU). A conditional
diffusion model generates symmetric channel layouts using maximum GPU temperature, GPU temperature spread, and pressure drop as performance targets. Generated designs undergo connectivity and dead-end-branch screening and are evaluated using a calibrated reduced-order thermal-fluids model. Based on 5,000 generated layouts, the multi-objective analysis identified the optimal design for thermal properties, with estimated maximum GPU temperature of 70.30 degree Celsius, GPU temperature spread of 24.90 degree Celsius, and pressure drop of 89.72 kPa. Compared to a conventional reference
topology, the optimal design reduced the maximum GPU temperature, temperature spread, and pressure drop by 33.6%, 52.5%, and 72.8%, respectively. High-fidelity three-dimensional conjugate heat-transfer simulation in OpenFOAM estimated a maximum GPU temperature of 66.70 degree Celsius and a pressure drop of 92.1 kPa, showing only differences of 8.6% in temperature rise and 2.6% in pressure drop. The results demonstrate that physics-guided generative design based on the reduced-order model can efficiently discover unconventional cooling channel architectures while reducing reliance on repeating computationally expensive simulation.
Read the full abstract ▾
Machine Learning
ReCoG: Reciprocal Co-Evolution for Multimodal Graph Learning
Rui Xue and Tianfu Wu
Multimodal graph learning requires jointly training over graph structure and heterogeneous node attributes, yet existing methods largely decouple these processes: prior
multimodal graph neural networks (GNNs) focus on aligning modalities in a shared
embedding space while operating on fixed or weakly adapted graph structures, and graph structure learning approaches infer
topology from unimodal node representations without accounting for
multimodal interactions. This separation fundamentally limits the ability of GNNs to capture semantically meaningful relationships in
multimodal settings, where observed edges are often noisy, incomplete, or misaligned with underlying semantics. We propose ReCoG (Reciprocal Co-
Evolution for
Multimodal Graph Learning), a new learning paradigm that tightly couples graph structure learning and
multimodal representation learning through end-to-end reciprocal interaction. Concretely, ReCoG integrates (i) a
multimodal graph refiner that infers and corrects edges using cross-modal semantic evidence, and (ii) a coupled cross-modal message passing mechanism that performs joint intra- and inter-modality propagation over the refined graph. This unified design yields greater expressiveness than decoupled or two-stage formulations and allows dynamic interaction between
topology and representation learning. Across diverse
benchmarks for node classification and link prediction, ReCoG consistently outperforms strong
multimodal graph structure learning baselines, including graph foundation models. Our results demonstrate that reciprocal co-
evolution of structure and semantics is important for effective
multimodal graph learning, challenging the prevailing separation between
topology and representation learning.
Read the full abstract ▾
Computer Vision
OmicSync: Reliability-Aware Spatial Multi-Omics Clustering with Evidence-Constrained LLM Reasoning
Rabeya Tus Sadia, Qiang Ye and Qiang Cheng
Spatial multi-omics technologies jointly profile gene expression, surface
proteins, and histology at each tissue spot, yet most spatial domain discovery methods provide only cluster assignments, without indicating assignment reliability, modality contributions, or why a domain decision should be trusted. We present OmicSync, a reliability-aware spatial multi-omics framework that couples unsupervised domain clustering with evidence-constrained LLM
reasoning using model-derived per-spot signals, including assignment confidence, epistemic routing uncertainty, and modality-routing weights. These signals are converted into structured evidence dictionaries and used to generate standard, stepwise, counterfactual, contrastive, and uncertainty-focused explanations. OmicSync integrates a KAN-GCN backbone with spatial encoding, cross-modal fusion, uncertainty-aware routing,
cell-type supervision, and missing-modality imputation. We further introduce OmicSync-R, which closes the
reasoning-clustering loop by using automatically computed
reasoning-quality scores as REINFORCE rewards, allowing
reasoning coherence to shape the latent structure without backpropagating through the
language model. Across four 10x CytAssist FFPE spatial proteomics
benchmarks, OmicSync achieves the best average rank on Human Tonsil (1.44), Glioblastoma (1.78), and Tonsil Add-on (1.22), and second-best on Human Breast Cancer (2.33). OmicSync-R further improves ARI on Human Breast Cancer from 45.73 to 46.72 and outperforms existing methods on six of nine clustering metrics. Together, OmicSync and OmicSync-R enable reliability-aware, spot-level auditable spatial domain discovery guided by evidence-constrained
reasoning.
Read the full abstract ▾
Machine Learning
Neural Operator based Multi-Field Reconstruction of Inner Solar Boundary State
Vignesh Kumar Pandian Sathia, Reza Mansouri, Dustin J. Kempton et al. (+2 more)
The
Solar wind is a continuous flow of charged particles emanating from the
solar surface and governed by complex, interacting magnetohydrodynamic processes. Accurate specification of inner-boundary conditions is essential for heliospheric modeling and
solar-wind prediction. In many practical applications, only a subset of interacting multi-field variables is directly available, but for a comprehensive view of
solar wind prediction and downstream magnetohydrodynamic simulations, a more complete boundary state is required. In this work, we study the problem of learning the multi-field multi-scale
solar magnetohydrodynamic state at 30
solar radii ($R_\odot$) using operator learning. Specifically, given the radial velocity and radial
magnetic field, we aim to reconstruct the non-radial velocity and
magnetic field components, radial and non-radial current density, thermodynamic density, and pressure components. This mapping is highly nonlinear, spatially coupled, and multi-scale, making it a challenging task for data-driven scientific machine learning. To address this problem, we employ a Local Neural Operator (LocalNO) that learns mappings between input and output function spaces while retaining locality and resolution-awareness. Unlike conventional regression models and autoencoder models, neural operators are better suited for learning structured field-to-field transformations arising from physical systems. The resulting predictions along with inputs are intended to serve as boundary condition variables for future inner-heliospheric modeling pipelines.
Read the full abstract ▾
All authors Vignesh Kumar Pandian Sathia, Reza Mansouri, Dustin J. Kempton, Pete Riley, Rafal A. Angryk
Computer Vision
Can We Perform Online RL for Image Editing without Editing Rewards?
Qichao Ma, Jikang Cheng, Ling Liang et al. (+3 more)
Reinforcement learning (RL) enables direct preference optimization for image editing through editing-specific rewards, which remain less developed due to costly triplet supervision and complex task-dependent calibration. In contrast, text-to-image (T2I) generation benefits from a mature and diverse reward ecosystem spanning semantic
alignment, aesthetics, realism, glyph shape, and other visual preferences. Extending this ecosystem to image editing would substantially broaden the range of visual preferences accessible to RL-based optimization, prompting the central question: Can We Perform Image Editing RL without Editing Rewards? In this paper, we argue that the standard image editing dimensions have potential to be mapped to the T2I reward space: image quality can transfer directly,
prompt following can be aligned through a description of the desired visual state, and reference consistency admits a coarse semantic conversion by encoding the source content to preserve. However, editing instructions specify relative changes, whereas T2I rewards require self-contained target descriptions; moreover, semantically valid captions from generic
vision-
language models may be incompatible with the frozen reward. Hence, we further introduce Lever-Edit, a two-stage framework that learns a reward-aligned captioner for counterfactual target descriptions, freezes it, and optimizes the editing policy solely with the transferred T2I reward. Experiments show competitive editing
alignment and source preservation against editing-reward-based fine-tuning, while outperforming intuitive transfer baselines.
Read the full abstract ▾
All authors Qichao Ma, Jikang Cheng, Ling Liang, Zhaofei Yu, Tiejun Huang, Renye Yan
Computer Vision
LagrangeGS: Non-Conservative Lagrangian System on Dynamic 3D Gaussian Splatting
Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda et al. (+4 more)
Dynamic 3D Gaussian Splatting (3DGS) achieves photorealistic reconstruction of time-varying scenes, and recent physics-aware extensions improve extrapolation by explicitly predicting velocity fields. However, these extensions merely fit vector fields to visual deformations without satisfying Lagrangian mechanics, leading to three major issues: (i) physically inconsistent trajectories, (ii) lack of time-reversibility, and (iii)
geometric collapse during long-term extrapolation. In this paper, we propose LagrangeGS, which formulates dynamic 3DGS as a non-conservative Lagrangian system. While this Lagrangian formulation fundamentally solves (i), a direct application of general LNNs to dynamic 3DGS requires a large velocity-Hessian inversion for millions of Gaussian particles. To overcome this computational bottleneck, we approximate the velocity-Hessian as an identity
matrix, decoupling particle dynamics for computational tractability. For (ii), we restrict the non-conservative forces to be explicitly time independent, enabling consistent backward integration. Finally, to address (iii), we introduce local rigid
alignment that regularizes particle trajectories. Extensive evaluations on dynamic scene
benchmarks demonstrate that LagrangeGS enables stable long-term extrapolation, consistent time reversal, and counterfactual physics-based editing without retraining.
Read the full abstract ▾
All authors Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda, Tomoyasu Shimada, Riku Inoue, Kazuhiko Murasaki, Ryuichi Tanida
Computation and Language
SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL
Yingnan Chen, Chun Ding, Tianshi Xu et al. (+2 more)
Text-to-SQL aims to translate natural
language questions into executable SQL queries over relational databases, requiring multi-stage structured
reasoning over database schemas and query constraints. However, existing methods treat this task as single-step generation, where models optimize entire SQL sequences without targeted feedback at key decision points and lack support for interacting with and controlling the intermediate generation process. To address this issue, we propose SPOC-SQL, which decomposes Text-to-SQL into four sequential subtasks following standard SQL execution logic and designs stage-specific optimization strategies for the model to learn key decisions. Specifically, we propose the implementation of fine-grained preference optimisation at key decision points across SQL stages, with the objective of enhancing structured decision-making during query construction. Furthermore, a structured decomposition strategy is designed, facilitating stage-wise intervention and correction through explicit intermediate representations. This results in more controllable and reliable SQL generation. Experiments demonstrate that incorporating stage-wise human knowledge consistently improves performance, validating the effectiveness of stage perception controllable generation.
Read the full abstract ▾
All authors Yingnan Chen, Chun Ding, Tianshi Xu, Xu Yang, Si Wu
Computation and Language
DelistBench: Evaluating Search-Enabled LLMs for Auditable Corporate-Event Database Completion
Xuan Yao, Shuping Li, Yang Dai et al. (+2 more)
Financial institutions need an independent way to detect missing, stale, and misclassified corporate-event records in vendor databases. We introduce Search-to-Record, a database-assurance task in which search-enabled large
language models reconstruct institution-defined event records from public sources for a known security universe and historical cutoff, and DelistBench, a 1,200-record
benchmark for security-level delisting announcements. We evaluate five models in paired closed-book and web-enabled conditions. Web access raises announcement-date accuracy within seven days by 34.0 to 48.0 percentage points and event-status accuracy by approximately 2.8 to 21.7 points; the best system achieves 81.5% overall joint accuracy within seven days. Economy web systems achieve 75.9-78.3% overall joint accuracy within seven days at 4.5-6.6% of the API cost of the most expensive web system. Risk-based triage identifies low-error subsets, although the highest-coverage operating point still sends 27.3% of the balanced test set to review. The evaluation identifies web
retrieval as the main source of timing gains and shows that low-cost systems can approach the best system's accuracy. Together, Search-to-Record, DelistBench, and the evaluation provide concrete deployment guidance: calibrate triage to local event prevalence and
market mix, preserve positive-event recall, and route positive and ambiguous cases to targeted review.
Read the full abstract ▾
All authors Xuan Yao, Shuping Li, Yang Dai, Yi Zhou, Ke-Wei Huang
Data Structures and Algorithms · Cross-listed from quant-ph
Classical and quantum spectral density estimation under local graph access
Rong-Hua Li, Meihao Liao and Yichun Yang
We study spectral density estimation for the normalized adjacency
matrix of an unweighted graph under local access model. Previously, Cohen-Steiner et al. [KDD 2018] proposed an
algorithm for $\varepsilon$-approximate spectral density estimation in the Wasserstein-1 distance, using $2^{O(1/\varepsilon)}$ local queries to the graph. In this paper, we prove that every constant-success
estimator with Wasserstein–$1$ error at most $\eps$ requires $2^{\Omega(1/\eps)}$ queries, showing that the Cohen-Steiner
algorithm is optimal up to constant in the exponent. This resolves the open problem left by previous researches Jin et al. [COLT 2023] and Peng et al. [COLT 2026]. We then turn to
quantum local access model. We give an $\widetilde O(\eps^{-3})$-query
algorithm estimating the spectral density with Wasserstein-1 error at most $\eps$. Finally, we prove a $\widetilde\Omega(\eps^{-4/3})$
quantum lower bound when the graph is sufficiently large. As a result,
quantum local access model changes the dependence on $\eps$ from exponential to
polynomial.
Read the full abstract ▾
Artificial Intelligence
The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory
Qi Feng, Chris Ding and Jicong Fan
Long-term
language-model
agents accumulate
memories across interactions, but their retrievers typically do not accumulate
retrieval experience. Semantic
retrieval is efficient, but
embedding similarity does not always reflect whether a
memory contains evidence relevant to the current query. Large
language model (LLM) rerankers provide stronger query-conditioned relevance scores, yet stateless reranking repeatedly scores a large candidate pool and discards these scores after each query. We introduce EARM, an experience-amortized reranking framework that treats previously acquired LLM relevance scores as reusable
retrieval experience. EARM stores sparse query–
memory relevance scores in an online
matrix, learns their shared structure through causal
matrix completion, and combines a small set of newly observed scores with estimated scores to rerank the remaining candidates. The scoring budget decreases as experience accumulates, changing LLM reranking from a repeated per-query expense into a
retrieval capability learned over an
agent's lifetime. Experiments on long-term conversational
memory show that mixed observed-and-estimated reranking improves answer accuracy over semantic
retrieval by up to 6.62% and remains effective when only 17.5% of candidates receive direct LLM relevance scores, thereby substantially reducing the inference overhead of LLM reranking. These results motivate a broader view of
agent memory: a long-lived
agent should remember not only past content, but also how that content has proved useful for
retrieval.
Read the full abstract ▾
Networking
Spatio-temporal Path Optimization for Stabilizer-Code-Protected Quantum Networks
Yuanbo Zhang, Qianfan Wang, Yangming Zhao et al. (+2 more)
Quantum Error Correction~(QEC)-protected direct transmission is a fundamental approach to preserve fragile
quantum states while they are physically forwarded across noisy
quantum networks. When a logical
qubit traverses multiple hops, selected QEC-capable nodes may recover the encoded state before it continues along the route. The feasibility and cost of the final transmission strategy therefore depend on how we jointly choose the path, the recovery locations, and the protection schemes. In this paper, we formulate and analyze a cross-layer spatio-temporal path optimization problem for block-style stabilizer-code-protected direct transmission. Our main results include fixed-scheme and flexible-scheme single-flow routing
algorithms, as well as a multi-flow routing
algorithm. The framework developed in this paper can serve as an algorithmic building block for QEC-aware routing under logical-error and logical-lifetime constraints. Simulations show that it reduces single-flow average routing cost by approximately 25–30% over Decode-Always and lowers multi-flow throughput-normalized congestion by approximately 28–31% over Greedy-Assignment.
Read the full abstract ▾
All authors Yuanbo Zhang, Qianfan Wang, Yangming Zhao, Lin Chen, Deke Guo
Machine Learning
Learning to Control Coupled-Dynamics Environments with Joint Markov Decision Processes
Ege C. Kaya, Aliasghar Pourghani, Mahsa Ghasemi et al. (+2 more)
Coupled-dynamics environments expose the one-step outcomes that would follow from several possible counterfactual actions under a common realization of exogenous randomness. The ordinary Markov decision process formalism allows one to reason about the marginal law of each action but discards dependence across these counterfactual outcomes. The Joint Markov decision process (JMDP) formalism preserves that dependence. Prior work established the formalism and solved the fixed-policy joint moment evaluation problem in JMDPs. This paper develops optimal-control methods. We define a nonparametric distributional Bellman optimality operator for JMDPs, and prove that when the induced marginal MDP has a unique optimal policy, its iterates converge in Wasserstein distance to the optimal joint return law. For the first two moments, we establish convergence under a weaker condition that permits several mean-optimal actions as long as their tie resolutions share a second-moment fixed point. We also derive sampled targets for neural approximation.
Read the full abstract ▾
All authors Ege C. Kaya, Aliasghar Pourghani, Mahsa Ghasemi, Vijay Gupta, Abolfazl Hashemi
Machine Learning
LpWM: A Case for Sparse Representations in World Models
Yilun Kuang, Yash Dagade, Quentin Le Lidec et al. (+3 more)
Joint-
embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-
entropy distributions such as isotropic Gaussians, yielding dense representations. However, it is unclear whether dense representations are the most favorable geometry for modeling dynamics. In this work, we ask whether a different geometry, sparse representations, can make action-conditioned latent dynamics easier to model, and what dynamical structure emerges from such representations. We first show that nonlinear Lipschitz dynamics can be approximated arbitrarily well by action-conditioned linear dynamics in a sufficiently high-dimensional one-hot latent space, with rollout error vanishing as the dimension grows. This motivates distributed sparse representations as a practical relaxation of one-hot sparsity. We introduce LpWorldModel (LpWM), a JEPA model regularized with Rectified Distribution Matching Regularization (RDMReg) to match encoder features to a Rectified Generalized Gaussian distribution, yielding non-negative sparse codes. Empirically, sparsity lowers the predictor complexity required for successful planning: on PushT, sparse LpWM outperforms dense LeWM by up to 57% in planning success at intermediate predictor capacities. This advantage also extends beyond Gaussian distribution matching, with LpWM outperforming dense VICReg representations across multiple predictor families. We further find that the learned sparse representations are mode-factored, with support encoding discrete dynamical regimes and feature magnitudes capturing continuous within-regime state. Together, these results suggest that sparse representations can reduce the predictor complexity required for control while revealing interpretable structure.
Read the full abstract ▾
All authors Yilun Kuang, Yash Dagade, Quentin Le Lidec, Lucas Maes, Randall Balestriero, Yann LeCun
Artificial Intelligence
Compositional Chain-of-Relations for Faithful Knowledge Graph Question Answering with Large Language Models
Chenhui Liu, Jianpeng Zhou and Jiahai Wang
Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large
Language Models (LLMs), and complex KGQA that requires multi-hop
reasoning is especially challenging. Solving a complex query involves two coupled phases: candidate
retrieval, which locates answer candidates over the KG, and constraint handling, which filters these candidates against the query constraints. Faithful
reasoning requires grounding both phases in the KG. However, existing
agent-based methods ground candidate
retrieval through entity-centric exploration, while leaving constraint handling to the LLM's internal knowledge, which leads to two critical limitations. (1) Unreliable entity
pruning: entity-centric exploration uses entities as search units and must prune them to a fixed-size subset at each hop. Because entity information in KGs is often incomplete and a fixed-size subset cannot retain all valid entities, such
pruning inevitably drops valid entities and ultimately leads to wrong answers. (2) Ungrounded constraint handling: query constraints are resolved from the LLM's internal knowledge rather than the KG, leaving the final answers unverifiable and prone to
hallucination. To address these limitations, this paper introduces a relation-centric exploration paradigm, which uses relations rather than entities as search units and thus avoids unreliable entity
pruning. Built on this paradigm, this paper proposes Compositional Chain-of-Relations (CCoR), a simple and effective framework that grounds both phases in the KG with two relation chains: a main chain for candidate
retrieval and a constraint chain that verifies query constraints through explicit KG exploration. Experiments on four KGQA
benchmarks show that CCoR consistently improves accuracy, faithfulness, and efficiency over strong baselines, with more pronounced gains on complex queries.
Read the full abstract ▾
Computation and Language
Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time
Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder et al. (+2 more)
Large
Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already present in context. Standard defenses such as repetition, presence, and frequency penalties and n-gram blocking act on
token recurrence rather than the sequential structure of a loop, and often suppress looping only at strengths that also degrade formatting or fluency. We propose Don't Repeat Yourself (DRY), a sampling-time logit adjustment that penalizes a candidate
token only when generating it would extend the current suffix into an exact continuation of a span seen earlier in the context. Sequence breakers protect chat templates and formatting
tokens. Across models from 1.5B to 120B parameters, nine
prompt families, and a 600-pair human study, DRY reduces suffix-extension rate by 47% while improving lexical diversity. An intervention-matched placebo produces no comparable reduction, identifying suffix matching as the operative mechanism. On AWQ-quantized 70B and 120B models, DRY reduces loop rate by roughly half while preserving MT-Bench, MMLU, and GSM8K performance, whereas standard alternatives lose measurable ground. DRY has been adopted by popular open-source LLM inference frameworks including llama.cpp, ExLlamaV2, and text-generation-webui, highlighting its practical impact on text generation.
Read the full abstract ▾
All authors Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz-Ziv
Computer Vision
ByteAction: Byte-space Action Recognition Foundation Model
Fangcheng Li, Zhen Yu, Kejun Wu et al. (+2 more)
Byte-space Action Recognition (BAR) aims to recognize human actions directly from compressed image bitstreams without any pixel decoding. By operating entirely in byte space, BAR is inherently independent of file integrity and pixel-level reconstruction, making it naturally applicable to
privacy-sensitive scenarios and robust against bitstream corruption. In this paper, we propose ByteAction, a BAR foundation model that achieves accurate action recognition on corrupted image bitstreams. ByteAction follows a dual-view byte-level recognition framework. It constructs weakly and strongly corrupted bitstream views, which are augmented by Bitstream Pattern Augmentation (BPA) and encoded with a shared ByteFormer backbone. The model is optimized with both classification and corruption consistency objectives. Specifically, we propose Bitstream Pattern Augmentation (BPA), which reshapes one-dimensional byte sequences into two-dimensional byte
matrix and applies region-level erasure to encourage the model to learn robust cross-region byte dependencies. We further propose a Corruption Consistency Training strategy that constrains the model to maintain stable predictions across different corruption severities through bidirectional KL divergence. Experiments on the image bitstream from Stanford40, PPMI, and PASCAL VOC 2012 Action demonstrate that ByteAction achieves state-of-the-art corruption robustness across all scenarios while maintaining competitive intact bitstream performance.
Read the full abstract ▾
All authors Fangcheng Li, Zhen Yu, Kejun Wu, Qiong Liu, You Yang
Computation and Language
XTC: Head-Aware Sampling by Excluding Top Choices
Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder et al. (+2 more)
Standard decoding rules for autoregressive
language models promote diversity by rescaling the full next-
token distribution or truncating its low-probability tail. These strategies overlook a common regime of open-ended generation in which several continuations are plausible but too much probability mass remains concentrated on the most generic choice. We introduce XTC (Exclude Top Choices), a lightweight head-aware decoding operator that targets this regime directly. XTC identifies
tokens whose probabilities exceed an absolute plausibility threshold $\tau$: when at least two qualify, it removes the dominant eligible choices with probability $\rho$ and retains only the weakest plausible alternative before renormalization. Across 60 experiments on Gemma 3 27B Q4, Gemma 3 12B Q6, and DeepSeek R1 14B Q6, with scaling validation on Llama 3.3 70B Q4, XTC improves the diversity-repetition Pareto frontier. On creative generation, Distinct-2 increases by 11–15% and repeat trigrams decrease by 27–47% across the four models. Combined with temperature scaling, gains reach 38% in Distinct-2 and 71% in repeat-trigram reduction over baseline. A blinded Amazon Mechanical Turk study with 150 Master raters yields a 62.3% creativity preference for XTC ($p<10^{-4}$) without reduced fluency, while a GPT-4o control judge reproduces the Anthropic-judge direction on every measure. On IFEval with Llama 3.3 70B Q4, XTC preserves
prompt-level strict accuracy within 1.7 percentage points of baseline while recovering most of the diversity gain; a temperature setting matched on Distinct-2 reduces IFEval by 8.8 points. The effect is additive with temperature and repetition penalties, robust across quantization levels and model families, and consistent across twelve
prompt genres. XTC has been adopted by llama.cpp, ExLlamaV2, and text-generation-webui.
Read the full abstract ▾
All authors Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz-Ziv
Computer Vision
Object-Uni: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
Mining Tan, Yinuo Wang, Ziqi Zhou et al. (+6 more)
Unified models for visual understanding and generation have made rapid progress, yet they still lack the ability to understand and manipulate the spatial states of object instances. Existing models can describe objects in natural
language, but they struggle to precisely represent continuous object poses and generate geometrically consistent images under target viewpoints. To mitigate this, we propose Object-Uni, a unified model for object-centric spatial understanding and controllable generation. Specifically, we formulate object-centric spatial intelligence as a unified problem connecting pose perception, spatial
reasoning, pose-conditioned generation, and object-centric novel view synthesis. We treat object pose as an explicit
geometric variable shared by understanding and generation, rather than merely a prediction label or control signal. To make pose usable by
multimodal large
language models, we propose a viewpoint-based orientation abstraction that maps orientation into structured viewpoint descriptions while preserving continuous
geometric supervision. We further construct an object-centric spatial
benchmark (UniSpatial-80K) and train a unified model with an object-
token-grounded pose anchor to associate each instance with its pose state. Experiments show that our model improves object-level pose understanding and pose-controllable generation, moving unified models from describing objects toward manipulating spatial states.
Read the full abstract ▾
All authors Mining Tan, Yinuo Wang, Ziqi Zhou, Weize Quan, Sifei Li, Jingdong Chen, DanDan Zheng, Libin Wang, Weiming Dong
Cryptography and Security
A Study of Bluetooth Access Control Based on NFT Soft Pairing
Zhiming Liang, Bin Chen, Ruijun Wu et al. (+3 more)
This paper proposes a Non-Fungible
Token (NFT) soft pairing framework for Bluetooth service access control. Unlike conventional Bluetooth systems where pairing implicitly grants persistent service access, the proposed approach decouples native Bluetooth pairing from authorization without modifying the underlying protocol stack. The framework introduces a three-layer architecture consisting of a Bluetooth layer for connectivity, a blockchain layer for trusted execution and on-chain state verification, and an application layer where NFT soft pairing defines the authorization logic. In this design, Non-Fungible Bluetooth
Tokens (NFBTs) represent user-side access credentials, while Non-Fungible Device
Tokens (NFDTs) represent device identities. Their bidirectional on-chain binding forms a revocable and verifiable NFT soft pairing relationship. During access, users prove ownership of valid NFBTs through challenge-response signatures, and devices verify the corresponding on-chain state before granting service access. A prototype implemented with MetaMask and Ethereum demonstrates secure authentication, dynamic revocation, acceptable latency, and gas-efficient credential issuance based on ERC1155.
Read the full abstract ▾
All authors Zhiming Liang, Bin Chen, Ruijun Wu, Zhe Peng, Chen Sun, Shuo Wang
Computation and Language
Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models
Bohan Yu, Pengfei Cao, Chen Han et al. (+7 more)
Large
language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided procedural rules at scale. To evaluate this capability, we introduce RuleWorld, a large-scale
benchmark that reformulates rules as globally reusable abstract units rather than instance-specific facts. In RuleWorld, several scenarios, including single-rule, parallel multi-rule, and multi-hop
reasoning, are settled for comprehensive evaluation. We further propose DynaRule, an end-to-end framework that injects the given rules into the KV cache and turns
retrieval into an internal, learnable, step-wise process. Specifically, DynaRule employs Stacked Step-Level
Attention Training with a special <search>
token to enable dynamic rule re-
attention and updating during inference. In this way, the model can re-attend to the most relevant rules at each step, dynamically replacing outdated ones to support more stable multi-step
reasoning. Experiments on RuleWorld show that existing LLMs face challenges under large rule pools, while DynaRule improves average QA accuracy by up to 19 points and achieves over 85% Recall@1 at 10K rules, outperforming strong baselines by large margins. We make our code and
dataset available here: https://github.com/SharkSpicy-NLP/Beyond-Factual-Knowledge.
Read the full abstract ▾
All authors Bohan Yu, Pengfei Cao, Chen Han, Chenxi Zhou, Zhiheng Zhang, Zhiyang Xie, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu
Artificial Intelligence
The Compaction Cliff in Long-Running AI Agent Memory
Saber Zerhoudi, Jelena Mitrovic and Michael Granitzer
A safety rule and an episodic log compete for the same
tokens in an AI
agent's context. When the budget overflows, both are summarized at the same rate; only the rule needs exact wording to remain enforceable. On 20 production
agent configurations, Claude Code's /compact
prompt on Sonnet 4.6 preserves 53% of safety rules after one compaction round and 10% after five. We name this the Compaction Cliff. We address it with Knowledge Triage, a framework that classifies each line of an
agent's knowledge base by type and routes each type through its own retention policy. Three deterministic operators implement this triage across the three context-management operations: TypeCompact rewrites items in place under per-type fidelity, TypeDecompose partitions a topic too large to compact safely, replicating in-scope safety rules across partitions, and TypeRetrieve fetches items from external storage with in-scope rules pinned ahead of relevance. On five public corpora, TypeCompact preserves 2–4$\times$ more safety rules than the strongest single-shot LLM compactor at every ratio, with 96% recall over five rounds. TypeDecompose reaches 0% locality violations against 93% under uniform partitioning. TypeRetrieve reaches 100% recall@50 against 73% for the best single-shot LLM retriever. On three downstream behavioral
benchmarks, we outperform the production Sonnet compactor on medical compliance (paired McNemar $p < 10^{-8}$ on preservation, $N = 200$), the full-policy and hierarchical baselines on retail task pass rate ($p < 0.01$, $N = 115$), and the hierarchical compaction on the airline domain ($p = 0.024$). We release AgentArtifactCorpus (396{,}934
agent configurations from 54{,}628 public GitHub repositories), the classifier, and the reference implementation.
Read the full abstract ▾