Computation and Language
Harness Annealing: Learning to Act with Less External Control
Yingxuan Yang, Huacan Chai and Ying Wen
Language agents rely on external harnesses to track state, organize workflows, and verify answers. Beyond providing tools and information, these harnesses supply control decisions about what to investigate, whether to revise, and when to stop. Training on successful harness-supported trajectories can improve task performance while leaving these decisions dependent on runtime intervention. We ask whether harness-supported experience can also teach the model to make these decisions, allowing the division of control to change as the model learns. We call this objective harness internalization: learning to assume specified control responsibilities while retaining task performance after the corresponding support is withdrawn. We introduce HARNESS ANNEALING TRAINING (HAT), which combines explicit control supervision with a curriculum over teacher trajectories collected under progressively weaker harnesses. Experiments with 9B and 35B models on SWE-QA and SWE-QA-Pro evaluate every checkpoint under four deployment harnesses. Selected annealed checkpoints operating with tools alone achieve scores close to those of their respective starting checkpoints deployed with the full harness. The benefits vary with model scale and deployment configuration, and further annealing does not uniformly improve performance. These findings suggest that harness-supported experience can help reduce the runtime control required by a trained
agent.
Read the full abstract ▾
Computation and Language
ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
Tarm Kalavantavanich, Teerawut Ponarchar, Pattaramanee Arsomngern et al. (+5 more)
Automatic SOAP note generation can ease the documentation burden on physicians, but existing
reasoning methods often omit clinically important information and generate unsupported content. Progress in Thai is further hindered by the lack of publicly available
datasets. We propose ASCRIBE, a physician-inspired
reasoning framework that ascribes a clinical-significance level to each extracted atomic fact in the conversation before summarization, making a general-purpose LLM a more reliable scribe. We also release ThaiClinicBench, the first de-identified Thai clinical summarization
benchmark of real encounters, together with a synthetic training corpus derived from real clinical notes. As a
prompt, ASCRIBE outperforms chain-of-thought prompting on GPT-5.4 and Gemini 3.1 Pro across the physician-aligned LLM-judge metrics and improves on standard prompting by up to 10.3 points on the completeness LLM-judge metric. As a GRPO reward, it enables a Gemma-4-E4B model trained solely on synthetic data to match Gemini 3.1 Pro in factual precision and surpass it in completeness. Code and data can be found at https://github.com/loolootech/ascribe.
Read the full abstract ▾
All authors Tarm Kalavantavanich, Teerawut Ponarchar, Pattaramanee Arsomngern, Jenta Wonglertsakul, Watcharakorn Chuthong, Chiraphat Boonnag, Knot Pipatsrisawat, Titipat Achakulvisut
Computer Vision
Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization
Zhen Zhou, Zhiwei Ning, Puhua Jiang et al. (+6 more)
Flow matching is central to 3D generation, yet in practice its reinforcement learning (RL) methods are largely adapted from 2D visual generation. Representative DPO-, GRPO-, and NFT-style objectives, when applied to negative trajectories, mainly steer predicted velocities away from the corresponding directions without explicitly specifying a target velocity field toward preferred samples. In 3D generation, constrained by pretrained model capabilities, rollout diversity, and reward-distribution complexity, directly applying these RL methods yields limited gains in
geometric quality. We introduce a forward-process RL method Dynamic Homing Optimization (DHO), which reformulates negative-trajectory optimization as positive-sample attraction-guided dynamic homing. Specifically, Minimum-Cost Attractive Matching (MAM) assigns each negative sample a distinct positive target, and Time-Aware Dynamic Correction (TDC) then redirects its trajectory toward the target using a remaining-time-aware corrective velocity. Building on asynchronous online DHO, we develop Flow3D-Pro, an image-to-3D geometry generation framework. Experiments show that DHO outperforms representative DPO-, GRPO-, and NFT-style objectives in 3D generation, while Flow3D-Pro produces higher-quality 3D geometry than existing mesh generation methods.
Read the full abstract ▾
All authors Zhen Zhou, Zhiwei Ning, Puhua Jiang, Sheng Zhang, Yifei Tang, Jie Yang, Xintong Han, Wei Liu, Chunchao Guo
Neural and Evolutionary Computing
Inherited Learning in an Artificial Ecology: How Controls and Update Allocation Shape Benefits
Xuening Wu, Lei Li and Shan Yu
Learning can improve an individual's behavior, yet a population risks losing that experience whenever individuals die and are replaced. Inheriting learned preferences offers a way to preserve useful behavior across generations, raising a question for artificial populations: when does inheritance improve collective performance, and how can its benefits be measured fairly? The challenge is that inheritance changes not only offspring behavior but also survival, reproduction, and opportunities for further hereditary updates. Random controls with equal update magnitudes may therefore yield misleading comparisons if they alter different states or obey different stability constraints. We investigate this problem in a resource-limited artificial ecology, combining structured random controls with interventions on newborn preferences and the allocation of hereditary updates. Preserving the state structure of random updates substantially narrows the apparent inheritance advantage, while a conditional establishment-speed benefit remains. Preference erasure and faster-learning compensation support a contribution from reduced offspring relearning. Update allocation also changes the comparison: event quotas and common time cutoffs can reverse rankings, although they also change realized update amounts. With update count and cumulative magnitudes matched, staged release improves occupancy but does not achieve the prespecified establishment criterion. These findings provide a framework for distinguishing the value of inherited preferences from the effects of control design and update allocation, clarifying how inherited learning should be evaluated in artificial populations.
Read the full abstract ▾
Computers and Society
Judgement in the Age of Jev: From Evaluation Scarcity to Evaluation Abundance
Richard Hill
Generative artificial intelligence has reduced the cost of producing plausible symbolic artefacts, leading recent organisation scholarship to identify evaluation and discernment as constraints under conditions of production abundance. This perspective examines a further possibility: that machine evaluation itself becomes inexpensive enough to be deployed routinely and at scale. The investigation is prompted by Jev, TypeSafe AI's specialised model for typed probabilistic decisions. TypeSafe explicitly invokes William Stanley Jevons to argue that lower-cost machine intelligence can unlock previously uneconomic uses. Treating this as a technological provocation rather than an established empirical result, the article formulates a conditional Jevons hypothesis for machine evaluation: sufficiently large reductions in the total marginal cost of usable machine evaluation may increase its organisational consumption where latent demand is substantial and complementary costs do not dominate. The article integrates rebound economics with research on cheap prediction, production abundance, machine evaluation, decision allocation, authority, reliance and Executive Judgement to examine this possible scarcity transition. It distinguishes prediction, machine evaluation, organisational judgement and authorisation as functional activities whose costs need not fall together. Evaluations can share evidence, criteria and errors; scale mis-specified rubrics; operate on representations from which consequential qualifications have disappeared; and change practical decision rights through thresholds and exception routing. The resulting research problem is when cheap machine evaluation substitutes for human evaluative work, when it redistributes or creates demands for judgement, and how it affects the grounds available at consequential organisational commitment.
Read the full abstract ▾
Artificial Intelligence
HHR: Hierarchical Hash Retrieval for Efficient LLM Generation
Lianjun Liu, Tiantian Zheng, You Huang et al. (+5 more)
Efficient long-context inference is essential for large
language models (LLMs), yet it poses a severe computational bottleneck. Hash-based
retrieval offers an efficient alternative by encoding queries and keys into binary codes and using Hamming distance for key selection. However, this leads to a critical mismatch between Hamming distance and
attention relevance. Query-Key logits depend jointly on directional similarity and feature magnitudes, whereas hash binarization discards magnitude information, causing both false-positive
retrieval of low-logit keys and false-negative omission of high-logit keys. To address these failures, we propose Hierarchical Hash
Retrieval (HHR), a coarse-to-fine framework that progressively improves
retrieval accuracy through Geometry-Aware Key Routing (GKR) and Learned Hash Projection (LHP). GKR learns a head-wise orthogonal transformation to redistribute feature magnitudes and derive more discriminative page-level logit bounds, enabling effective
pruning of low-logit keys while preserving important candidates. LHP then learns a head-wise projection space that aligns Hamming distance with the true Query-Key relevance ranking for fine-grained
retrieval. By combining GKR and LHP, HHR suppresses false positives and recovers false negatives, substantially improving the fidelity of hash-based sparse
attention. Extensive experiments across diverse LLMs and
benchmarks demonstrate that HHR achieves superior performance over existing methods. For example, on LongBench, HHR improves the average score by 1.10 points and, at a context length of 128K, achieves up to a 3.30x decoding speedup and a 2.83x end-to-end speedup for Llama-3.1-8B-Instruct. The code is publicly available at https://github.com/lianjunl13-sudo/HHR.
Read the full abstract ▾
All authors Lianjun Liu, Tiantian Zheng, You Huang, Weiqi Yan, Mingte Qiu, Huazhong Liu, Xiaofeng Zhu, Yunshan Zhong
Computer Vision
A Compact Explicit 4D Representation for Dynamic Scenes
Di Yang, Zhihao Li, Yanhai Xiong et al. (+1 more)
A compact dynamic-scene representation must retain both the surfaces seen over time and the appearance needed to render them from new viewpoints. We present Sparc4D, a feed-forward autoencoder that encodes a
monocular video with known cameras into a sparse 4D scene state. Static features are shared across the clip, while spatially anchored temporal slots store time-varying features with a median $5.0\times$ fewer values than per-frame storage and negligible change in the complete model's novel-view quality. A sparse decoder produces 2D Gaussian surfels, while stored source pixels preserve fine texture through
geometric re-projection. The state includes one full source frame and dynamic-region pixels sampled every fourth frame, alongside learned features and sparse occupancy. For a 32-frame MultiCamVideo clip, it averages 0.67M 32-bit-equivalent values on random windows and 0.66M on the first-32 protocol. On first-32, Sparc4D reaches 21.97 dB, compared with 20.40 dB for MoVieS. On randomly placed windows, their PSNR scores are comparable. Without fine-tuning on real data, Sparc4D transfers to DyCheck and Neu3D, where stored texture improves LPIPS while slightly reducing PSNR. Frozen Sparc4D features also support a manipulation policy that reaches 81.3% success on ManiSkill3 StackCube from 1,000 demonstrations.
Read the full abstract ▾
All authors Di Yang, Zhihao Li, Yanhai Xiong, Yufei Wang
Information Theory
Task-Oriented Boolean Function Computation: Practical Code Constructions
Yangshuo He, Guanding Yu and Jingge Zhu
Task-oriented communication conveys information that is necessary for downstream tasks. For binary decision tasks, this paradigm is information-theoretically formalized by Boolean function computation (BFC) via channels, where the receiver aims to determine the value of a function unknown to the transmitter. In this paper, we devise a practical code construction for the BFC problem based on a Reed-Solomon code. For noiseless binary channels, we derive finite-blocklength worst-case error bounds. By defining a rate function that captures how supported message length scales with channel uses, we characterize the rate-reliability tradeoff for different Boolean function families. With respect to this rate function, the proposed construction achieves an asymptotic computation rate of $1/2$. We further extend this construction to noisy channels by packing multiple BFC tasks into a single block and concatenating them with a conventional channel code. The corresponding finite-blocklength guarantees are expressed in terms of effective channel uses per function evaluation. With a channel code rate $R_c$, this construction achieves an asymptotic computation rate of $R_c/2$, yielding $C/2$ when capacity-achieving channel codes are employed. Numerical results illustrate the derived bounds and demonstrate substantial performance gains over conventional transmission. As examples, the proposed scheme achieves SNR coding gains of approximately $3.4$ and $6.4$ dB at an average task error probability of $10^{-5}$ for the exact-weight and rank-test tasks, respectively.
Read the full abstract ▾
Machine Learning
Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
Takumi Hara and Kanata Suzuki
Latent world models plan by scoring candidate action sequences with distances in latent space. However, task success is judged by physical quantities, which we call the success-criterion quantities. In all four latent world models we examine, the end-effector position is encoded in the latent state with an error larger than the success criterion allows. Such a latent state cannot separate successful candidates from failing ones. We propose an auxiliary loss that uses success-criterion quantities as training targets, whereas existing latent world models take them only as inputs. During training, a linear head on the encoder and predictor outputs regresses the success-criterion quantities, and the regression error is added to the training loss. The head is discarded after training, so the model, its cost, and its inputs at test time are unchanged. This loss alone improves the success rate on PushT and cube by 3.5% and 3.4% (absolute), respectively, and both improvements are statistically significant. A success criterion thus specifies what a world model must retain in its latent state, and we show that it can serve directly as a training target.
Read the full abstract ▾
Machine Learning
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
David Berghaus
Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large
language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping the best-scoring detector it finds. The loop discovers two compact detectors, one for univariate and one for multivariate series, that describe short windows by their local spectral features and compare them with the training-region distribution through a covariance-aware distance. On the TSB-AD
benchmark these detectors lead the field across metrics, ahead of the strongest classical, deep, and foundation-model baselines including Time-RCD, yet they train no network and use no GPU, and the multivariate detector is faster than every similarly performing baseline. LLM-driven program search is thus a practical route to accurate, efficient, and transparent detectors.
Read the full abstract ▾
Artificial Intelligence
Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models
Celso de Melo, Zishan Feng, James Hale et al. (+3 more)
As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their propensity to cooperate – and the signals that shape this propensity – has become essential. We examine cooperative behavior in frontier Gen AI models using the iterated prisoner's dilemma, manipulating counterpart reputation (positive, unknown, negative), strategy (extortion vs. generosity), and non-verbal emotional signaling (facial expressions conveying competitive or cooperative appraisals). In a first study with non-
reasoning models (Claude 3.5, Gemini 2.0 Flash, GPT-4o), cooperation was systematically shaped by all three factors, paralleling patterns long documented in human behavioral research, though models varied substantially in how heavily each factor was weighted. A second study with
reasoning models (Claude 4.6, Gemini 3, GPT-5.2) revealed a more concentrated reliance on strategy and reputation, a near-elimination of the Potemkin effect observed in non-
reasoning models (evidenced by near-uniform cooperation in a diagnostic harmony game), and a more conditional role for
emotion consistent with a hierarchical cue-weighting strategy rather than a simple loss of social sensitivity.
Reasoning models also showed heterogeneous end-game behavior, ranging from sustained cooperation to systematic last-round defection effect, revealing model-specific exploitability profiles with direct practical relevance for deployment in negotiation and other multi-round interactions. Together, these findings characterize Gen AI models as increasingly sophisticated, though heterogeneous, social actors, and underscore the practical value of developing standardized cooperation
benchmarks to inform the responsible deployment of Gen AI in interactive, socially consequential settings.
Read the full abstract ▾
All authors Celso de Melo, Zishan Feng, James Hale, Kazunori Terada, Giorgio Coricelli, Jonathan Gratch
Systems and Control
Learning-Based Predictive Control Method for Vehicle Lateral Control with a Multi-Step Gaussian Process Regression Prediction
Hasan Zakeri and Baisravan HomChaudhuri
We introduce a novel approach to model predictive control that incorporates multi-step uncertainty prediction for safely controlling systems characterized by uncertainties dependent on both state and control variables. The discrepancy between real-world systems and their control-oriented representations arises from inherent uncertainties, which frequently correlate with state and control variables, a common occurrence in modeling errors. As these uncertainties accumulate and propagate over time, they can produce substantial deviations over extended horizons, potentially compromising the integrity of safety-critical applications. Although existing
stochastic control frameworks can maintain system operation within safety boundaries at specified confidence levels, they necessitate accurate prediction of state distributions throughout the control horizon. This prediction represents a significant challenge for systems where uncertainties vary with state and control inputs. Our contribution addresses this challenge through a Model Predictive Controller leveraging multi-step Gaussian Process Regression to capture and anticipate uncertainties that are state- and control-dependent. We further propose an iterative solution to the optimization problem in our MPC framework and discuss the convergence of the
algorithm. To demonstrate the method in a practical application, we conduct an in-depth analysis of vehicle lateral control, particularly during lane-changing maneuvers, examining how errors propagate through the system model. The effectiveness of our proposed methodology is validated through comprehensive simulations.
Read the full abstract ▾
Robotics
EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation
Yiwei Qian, Shanze Wang, Qingyuan Hu et al. (+2 more)
Simulation-to-
robot transfer can fail when velocity commands produce motion and feedback that differ from those modeled during policy training. We present execution-interface dynamics adaptation (EIDA), which fits these responses from target-platform execution data without reconstructing actuator dynamics. A model of body-frame pose increments updates simulator geometry, while a separate model predicts the velocity feedback observed by the policy; a short history of velocity feedback is included in the policy input. The fitted models are used within a lightweight GPU-parallel simulator. On the full Jackal and Go2 validation sets, the fitted models reduced position and yaw prediction errors relative to the simulator's predefined motion model. Across 100
benchmark navigation environments evaluated in a separate physics-based simulator, EIDA achieved the highest success rate and
navigation score among the compared learned policies, both with and without global guidance. Feedback ablations further supported the need to match policy-facing velocity estimates. On a physical Unitree Go2, EIDA reached the goal without collision in all 20 static-scene trials, compared with 4 of 20 for the baseline. These results show that execution-interface adaptation can improve
navigation transfer without detailed actuator simulation.
Read the full abstract ▾
All authors Yiwei Qian, Shanze Wang, Qingyuan Hu, Xinming Zhang, Wei Zhang
Computation and Language
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Giulio Zeloni, Enrico Lo Conte, Salvatore Rionero et al. (+3 more)
Enterprises adopting
retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining deterministic checks, local guardrails, and structured LLM evaluation; a stratified beta-binomial gate that quantifies regression risk probabilistically; and a mandatory meta-evaluation protocol to validate the LLM judge before it influences decisions. Since engagement data is proprietary, we evaluate the judge layer on RAGBench, a public
benchmark of 100k annotated RAG traces across 12
datasets. On identical stratified test samples (N=1200 per judge), a low-cost judge (gpt-4.1-nano) detects non-adherent answers barely above chance (AUROC 0.603 [0.570, 0.634]), despite producing flawless protocol output, while gpt-4o reaches 0.783 [0.756, 0.807] – yet its per-domain performance still ranges from 0.62 to 0.88. A fixed-seed gate study spanning regression, no change, and improvement quantifies unsafe promotion, false-alarm cost, and improvement throughput. Under regression, the decision-grade profile reduces unsafe promotion to 22.2%-35.1%, against 29.3%-41.8% for a naive gate. These results support the design choices that judge quality must be measured per engagement and that point estimates alone are not a release decision.
Read the full abstract ▾
All authors Giulio Zeloni, Enrico Lo Conte, Salvatore Rionero, Giuseppe Santoro, Alessandro Rastelli, Fabio Sorrentino
Computer Vision
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
Cheng Yang, Yifan Wu, Yutao Huang et al. (+18 more)
GUI
agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows. However, the diversity of available trajectories is constrained by the applications, interface states, and workflows accessible in the underlying environments. Expanding this coverage requires deploying increasingly diverse and complex software, with specialized applications imposing additional installation, configuration, and runtime costs. We introduce AutoGUIWorld, a data generation framework that combines the visual priors of image generators with the task knowledge of a planner to synthesize GUI interaction trajectories without deploying or running the corresponding software environments. AutoGUIWorld samples initial GUI scenes from structured specifications of operating-system context, visual appearance, and interface state, and generates tasks conditioned on those scenes. A planner then specifies atomic actions and their intended visual consequences, while an image generator iteratively edits the current screenshot to produce subsequent observations. Action grounding and transition-level quality filtering yield 79,266 spatially annotated step-level training samples across Ubuntu, Windows, macOS, and Chrome. Fine-tuning Qwen3.5-35B-A3B on AutoGUIWorld trajectories improves the mean task score on OSWorld from 33.0% to 40.8% and the task success rate on ScienceBoard from 14.0% to 32.2%. These results show that generated trajectories improve GUI-
agent performance on real desktop and scientific tasks.
Read the full abstract ▾
All authors Cheng Yang, Yifan Wu, Yutao Huang, Zhaohua Zhang, Beiduo Chen, Muxi Chen, Chenchen Zhao, Hexuan Deng, Haolin Yang, Geyuan Zhu, Sa Zhu, Jianhuan Zhuo, Qiuyong Xiao, Jianhao Ruan, Yiran Peng, Jiayi Zhang, Tian Ye, Xinlei Yu, Tianwen Jiang, Jihong Zhang, Yuyu Luo
Computational Engineering
From language-model stock rankings to testable economic rules: A computational audit
Shuai Wu, Xue Li, Zhijun Wang et al. (+4 more)
We test the stability, reproducibility and investment outcomes of
language-model stock rankings. Four models and five numerical comparators share a portfolio engine over 72 monthly holding periods in the Shanghai Stock Exchange (SSE) 50, China Securities Index (CSI) 300 and CSI 500. Rankings use nine characteristics, and five repeated SSE 50 runs measure variation under identical inputs. Linear rules fitted to development-period model preferences are frozen before unseen-month, larger-pool and controlled-intervention tests. Their mean Spearman agreement with model rankings is 0.923-0.984 in the SSE 50 and 0.795-0.985 after transfer. Aggregate rank-change error falls relative to a zero-change prediction in twelve archived feature-group comparisons and eight matched single-feature comparisons, with Holm adjustments applied in separate nine-plus-three and six-plus-two families. Prediction of individual entries and exits remains weak (event Jaccard 0.000-0.125). Historical mean model compound annual growth rates range from 6.26% to 11.17%. At 10 basis points per side and six-month blocks, the twelve-comparison model-minus-rule return family and factor-controlled associations yield no adjusted finding. Three higher-cost, twelve-month-block comparisons favor a Terra rule within their twelve-test slices, with no adjusted finding across the full 144-test sensitivity grid. Two input-intervention batches totaling 5,184 responses supply paired intervention-return tests. The three-model batch has no bootstrap-adjusted finding at the primary block length; a Luna row-order effect appears under heteroskedasticity- and autocorrelation-consistent (HAC) adjustment within its three-test family but not in a pooled 24-test adjustment. Compact rules approximate aggregate rankings; return conclusions depend on comparison families, uncertainty methods and tie priorities.
Read the full abstract ▾
All authors Shuai Wu, Xue Li, Zhijun Wang, Bolun Liu, Weilin Cai, Zihao Su, Ran Wang
Computer Vision
EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes
Hongming Fu, Jingcheng Shi, Wenjia Wang et al. (+2 more)
Egocentric video has become a primary source of supervision for
embodied models, and its value rests on recovering hand motion in world coordinates, which camera motion and hand occlusion make difficult. Existing reconstruction pipelines typically separate hand and scene estimation, leave interaction attributes to separate task-specific models, and invoke several models per
video, so no prior reconstruction model estimates these attributes and throughput becomes a practical constraint on large-scale annotation. We therefore introduce EgoFound3R, a unified end-to-end model that estimates world-space hand geometry in a metric scale shared with the scene, and predicts point-wise interaction attributes, including visibility, contact, and distance. The model integrates three designs: (i) structured hand
prompts that transfer pretrained
geometric priors to world-space hand reconstruction; (ii) an explicit hand representation that decodes hand geometry and interaction attributes; and (iii) a shared-parameter multi-rate design that lowers inference cost. Together, these designs predict hand geometry and point-wise attributes in one pass. On OakInk-v2, TACO, and HOI4D, EgoFound3R reduces the mean per-joint position error (MPJPE) by 43.2%, 22.4%, and 11.6% over previous methods and predicts point-wise contact and distance alongside the geometry in the same pass, while attaining approximately 6x higher throughput.
Read the full abstract ▾
All authors Hongming Fu, Jingcheng Shi, Wenjia Wang, Binhua Zuo, Bo Zhao
Artificial Intelligence
Dependency-Aware Reward Shaping for Agentic Reinforcement Learning
Ziyi Chen, Yan Zhang, Jianhui Wei et al. (+2 more)
When training large
language models with reinforcement learning, terminal rewards provide little guidance about which steps matter. Common methods for assigning step credit overlook that work built on uncorrected mistakes is wasted while independent work remains valid. With only a final success/failure reward, every step in a failed episode has zero total future reward, even when it made progress. We propose Dependency-Aware Reward Shaping (DARS), which represents task progress as predicates linked by prerequisite relations and assigns step-level credit over the dependency graph. An annotator marks which predicates each step verifies, invalidates, or repairs. Verified predicates are discounted according to graph distance from the nearest broken prerequisite, while independent predicates are unaffected. Repairs update these weights based on any errors that remain; invalidated predicates need re-verification to regain credit. A fixed potential converts these annotations into signed per-step rewards. A common reward and annotation interface allows DARS to integrate with a range of
reasoning and agentic training methods, such as GiGPO and ARPO/AEPO, without changing their rollout strategies or optimizers. Across five task families and models from 1.5B to 8B, DARS improves success by up to 10 points over GiGPO trained with the same budget and harness (ALFWorld), raises the WebShop task score and Search-R1 QA accuracy, complements AEPO's
entropy-based training on AIME24/25 with a Python interpreter, and exceeds OmniOPD in controlled tool-free
reasoning comparisons at 1.7B and 4B. Ablations show that step-level credit, dependency attenuation, and graph
topology each contribute. On ALFWorld, a distilled 8B annotator matches the API annotator, enabling DARS to run efficiently without a frontier judge. Code is available at https://github.com/JianhuiWei7/DARS.
Read the full abstract ▾
All authors Ziyi Chen, Yan Zhang, Jianhui Wei, Daoan Zhang, Zuozhu Liu
Computer Vision
Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction
Ziting Wen, Runrong Deng, Zili Zhang et al. (+5 more)
Partially transmissive screens and protective covers are common in robotic inspection, but they create mixed
LiDAR returns from both the foreground material and the scene behind it. Conventional peak-based
LiDAR usually discards weak hidden returns, while single-
photon LiDAR records time-resolved histograms that preserve attenuated and overlapping echoes. However, existing transient reconstruction methods typically fit a single scene representation to the measured waveform. Under occlusion, weak or nearby foreground–hidden echoes can form a broad peak or subtle shoulder. Because such waveforms can also be explained by a displaced single surface or a thick density distribution, accurate transient fitting does not necessarily imply correct geometry. We propose a state-aware framework for foreground-view and hidden scene reconstruction from occluded single-
photon histograms. For each ray, we estimate local echo evidence, identifying no reliable surface evidence, single-return evidence, or two returns. The inferred echo state routes supervision for a two-head neural field: all rays constrain waveform reconstruction, while reliable anchors provide geometry localization. We also introduce a real paired single-
photon LiDAR occlusion
dataset with occluded and clean captures at fixed poses. Experiments on a real
dataset show improved hidden scene depth and point-cloud accuracy over baselines. Our results demonstrate single-
photon layered reconstruction as a practical route for 3D perception through partially transmissive occluders.
Read the full abstract ▾
All authors Ziting Wen, Runrong Deng, Zili Zhang, Haitao Zheng, Yuecong Xu, Xiaoqiang Ren, Guodong Shi, Kemi Ding
Computer Vision
Semantic RGB–Depth Based Surgical Skill Assessment in Microscopic Stereo Videos
Jecia Z. Y. Mao, Sue M. Cho, Francis X. Creighton et al. (+3 more)
Objective assessment of microsurgical technical skill is essential for competency-based training and quality assurance, yet existing
video-based approaches predominantly rely on RGB images and therefore overlook the 3D spatial relationships that characterize instrument-anatomy interactions. Although stereo operating microscopes provide complementary depth information, conventional stereo matching
algorithms can produce sparse and unreliable depth estimates under high-magnification imaging conditions, limiting their use for automated skill assessment. This work presents a semantic RGB-Depth framework for
surgical skill assessment from microscopic stereo
videos. A regression-based depth fusion method combines sparse metric stereo depth with dense
monocular depth estimates to generate a dense
geometric representation of the
surgical scene. This representation is integrated with semantically decomposed RGB streams corresponding to individual
surgical instruments and surrounding anatomy. A hierarchical
attention architecture jointly encodes these streams to capture discriminative patterns of instrument use and instrument-anatomy interaction across surgeons at different training levels. The framework was evaluated on 33 ex vivo transoral microlaryngeal procedures performed by six surgeons, comprising attending surgeons and
surgical residents, using leave-one-surgeon-out cross-validation. The proposed semantic RGB-Depth model achieved an F1 score of 0.938 for skill-level classification, compared with 0.696 for semantic RGB and 0.929 for semantic depth. These results suggest that
geometric information can improve automated
surgical skill assessment from microscopic stereo
videos. The learned spatial, temporal, and semantic
attention patterns also support qualitative examination of the scene regions,
video segments, and semantic streams emphasized by the model.
Read the full abstract ▾
All authors Jecia Z. Y. Mao, Sue M. Cho, Francis X. Creighton, Deepa Galaiya, Russell H. Taylor, Manish Sahu
Machine Learning
Autoregressive Drillhole Modelling Under Distribution Shift
Yihao Ding, Daniel Yitian Su, Yiran Zhang et al. (+2 more)
Autoregressive modelling has achieved remarkable success in
language and sequence tasks by learning to predict future states from previous observation. Mineral-exploration drillholes provide a natural but largely unexplored setting for this paradigm: as drilling proceeds, lithology is revealed sequentially from shallow to deep, making prediction of deeper strata inherently autoregressive. Existing drillhole modelling, however, is dominated by spatial interpolation and reconstruction, or largely rely on masked modelling, leaving strictly autoregressive prediction largely underexplored. We introduce DrillBench, a
benchmark of 49,671 Western Australian drillholes for next-layer prediction and autoregressive stratigraphic generation across a graded transfer spectrum, from local prediction through spatial shift to cross geological province transfer. Benchmarking classical, geostatistical, and neural models reveals a clear transfer boundary: spatial and geochemical conditioning provides large local gains but deteriorates sharply under stronger shift, whereas lithology-sequence autoregressive models transfer more robustly. Guided by this finding, we develop a backbone-agnostic recipe combining large-scale pretraining on historical drillholes with spatial
retrieval of neighbouring lithology.
Retrieval is most effective in weathered cover, when local spatial continuity remains informative, whereas pretraining contributes more strongly in bedrock and under broader geological shift. Together, they retain strong local performance while improving generalisation under spatial and cross-province shift, most markedly on the most distant splits. The
benchmark and code are available at https://github.com/yihaoding/drillbench.
Read the full abstract ▾
All authors Yihao Ding, Daniel Yitian Su, Yiran Zhang, Christopher M. Gonzalez, Wei Liu
Software Engineering
CompProv Produces Machine Readable Graphs Encoding Microscopic Algebraic Provenance for Reproducible Computation
Minas Abramyan, Mohammed Alaa Ala'anzy and Nasir Saeed
The reliability of computational results in scientific research and financial modeling increasingly depends on verifiable traceability, not merely on trust in a reported output. Existing provenance systems operate at the granularity of files,
datasets, or pipeline stages, leaving the internal sequence of algebraic transformations connecting an
algorithm's inputs to its outputs unrecorded; a rounding error, an undocumented substitution, or a missing intermediate value can propagate to a final result with no recoverable trace. This work presents CompProv, a Java-based, audit-oriented provenance framework that captures lineage at the atomic level of individual algebraic operations by encapsulating numerical values in high-precision wrapper objects, producing a serializable Calculation Provenance Graph (CPG) that persists as a self-contained artifact rather than a discarded byproduct. The framework is evaluated through three heterogeneous case studies: a decentralized-finance NAV calculation, a reconstruction of an interferometric gauge-block calibration in metrology under explicitly documented input assumptions, and a hydrological model performance evaluation. Deterministic replay reproduced each result exactly in a fresh environment, and CPG-based input substitution supported sensitivity analysis without exposing the underlying source code. These results indicate that, provided the CompProv runtime and wrapper classes are available in the replay environment, a CPG allows numerical integrity to be audited without disclosing proprietary business logic, and that its self-contained structure supports temporal auditability once an execution environment has become deprecated. This framework establishes an operation-level foundation for auditable-by-design computational systems, with scaling to high-throughput computing identified as a direction for future work.
Read the full abstract ▾
Computer Vision
iSEE: Object Permanence Through Self-Supervision
Pramish Paudel, Ajad Chhatkuli, Luc Van Gool et al. (+1 more)
Object permanence, keeping track of an object's identity and position while it is occluded, is central to
video representations that track, predict and plan. Trackers that achieve it learn from boxes, track identities and visibility labels. On the other hand, self-supervised object-centric methods discover objects without labels: through slot
attention, it represents a
video as slots that bind to objects and follow them across frames. However, these slots are lost under occlusion, making the desired permanence impossible.
Reasoning permanence is a hard problem because it requires to detect when an object becomes occluded, re-identify when object reappears, and keep the object's hidden position continuous, using reapperance as the only learning cue. To address this, we propose iSEE, a novel framework that offers all three aforementioned requirements, without any labels whatsoever. We built iSEE using the following three proposed components: (i) Object evidence modelling: a slot's
attention, compared with its own past, reveals when its object is hidden. (ii) Appearance-position separation: two slot streams let the appearance be held for re-identification while the position keeps changing. (iii) Permanence from reappearance: a walker follows the hidden object's position, trained only on where the object reappears. On LA-CATER static, iSEE returns a reappearing object to its own slot after 86% of occlusions, against 32% for SlotContrast, and localises it while hidden within 4.1 mAP of the label-trained SoTA RAM. The two streams also allow downstream planning, with the position stream as the action of a world model. Project page: https://insait-institute.github.io/iSEE/
Read the full abstract ▾
All authors Pramish Paudel, Ajad Chhatkuli, Luc Van Gool, Danda Pani Paudel
Machine Learning
Low-Budget Active Learning through Entropic Optimal Transport
Rim Hajal, Mathieu Besançon and Jérôme Malick
We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high accuracy on the selection only. This problem is particularly relevant in contexts where labeling requires costly expert intervention, as in medical applications. We leverage features extracted from a pretrained self-supervised model to represent the data, and perform coreset selection directly in this feature space. In this paper, we use entropic optimal transport, specifically the Sinkhorn divergence, as the coreset selection criterion, which first allows us to get dimension-free sample complexity results, and second admits computationally efficient gradient evaluations. This opens the way to using gradient-based
algorithms to rapidly compute solution candidates, further improved by a swap-based local search, with guarantees on the solution quality. Experiments on image
benchmarks and medical
datasets show that our method outperforms state-of-the-art heuristics in low-budget settings.
Read the full abstract ▾
Programming Languages
Associativity and Commutativity in Equality Saturation
Tarik Rosin, Marcel Ullrich and Sebastian Hack
Equality saturation is a promising technique for program optimization which sidesteps the phase ordering problem. However, current e-graph implementations grow exponentially large, even for simple examples. Many practical applications involve associative and commutative (AC) operators. We present an extension of relational e-matching that handles AC operators natively by storing terms as multisets. Preliminary results show that equality saturation modulo AC uses asymptotically less
memory in certain cases.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from math.OC
On solving integer bilevel optimization problems with a non-convex quadratic follower objective function using disjunctive cuts
Kübra Tan{\i}nm{\i}ş, Elisabeth Gaar, Jon Lee et al. (+2 more)
In this work, we study bilevel optimization problems where all variables are integer, all constraints and the leader objective function are linear, and the follower objective function is non-convex quadratic. Relying on bilevel-free sets derived from improving directions, we develop a disjunctive cut approach to exclude bilevel-infeasible solutions within a branch-and-cut
algorithm. We show that our disjunctive cuts can be obtained by solving a cut generating linear program. Furthermore, we discuss conditions that allow the number of disjuncts in the cut generating linear program to be reduced, and we propose several strategies to identify improving directions and generate disjunctive cuts efficiently. We evaluate various aspects of the proposed branch-and-cut
algorithm on both convex instances from the literature that fit our setting and new non-convex instances and compare the performance of our best approach with existing state-of-the-art approaches, which we significantly outperform.
Read the full abstract ▾
All authors Kübra Tan{\i}nm{\i}ş, Elisabeth Gaar, Jon Lee, Ivana Ljubić, Markus Sinnl
Artificial Intelligence
Qiang Yang, Zhiqiang Kou, Xueyi Zhang et al. (+6 more)
Large
language model (LLM)
agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowledge. Yet such experience is distributed across organizations and cannot be directly shared because of
privacy and proprietary constraints. Conventional
federated learning is insufficient for this setting, as
agent capabilities extend beyond model parameters to
memory, tools, rewards, skills, and structured knowledge. In this paper, we formulate
Federated Agent Optimization (FAO), which studies how distributed
agents can collaboratively improve through controlled information exchange while keeping raw data, complete trajectories, and private knowledge local. We define FAO as a multi-objective problem balancing
agent utility,
privacy leakage, and communication cost, and organize its optimization space across policy,
memory, tool use, reward, and structured knowledge and skills. We further characterize how private experience can be abstracted, protected, aggregated, and adapted into transferable capabilities, providing a unified view of how
agents can benefit from one another without direct experience sharing. Finally, we identify the key challenges of FAO and outline several promising directions for future research toward trustworthy
federated agent systems.
Read the full abstract ▾
All authors Qiang Yang, Zhiqiang Kou, Xueyi Zhang, Dong-Dong Wu, Hanlin Gu, Jing Guo, Yang Liu, Di Jiang, Qian Xu
Machine Learning
Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates
Yunrui Guan, Krishnakumar Balasubramanian and Shiva Prasad Kasiviswanathan
Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual assignment mechanism. We develop a flow-matching approach that combines a sample-split, doubly robust training objective with a learned coupling between observed source outcomes and target outcomes drawn from a fitted conditional outcome model. To enable finite-step generation, we leverage a score-corrected
stochastic sampler based on a Gaussian-smoothed interpolation. Our main theoretical contribution is a coupling-sensitive KL bound for constant-step Euler discretization: the error is controlled by moments of the source–target displacement under the chosen coupling, rather than by global uniform regularity of the velocity field, and has near-linear dependence on the ambient dimension. We also establish finite-sample non-parametric guarantees for the learned velocity and score fields when both the conditional outcome model and the source-target coupling are estimated from data. These bounds separate approximation, coupling-replacement, nuisance-estimation, generalization, and Monte Carlo errors and, combined with the sampler analysis, yield an end-to-end guarantee for counterfactual generation. Experiments on synthetic and semi-synthetic image
benchmarks support the coupling-dependent theory and show that, at finite discretization budgets, the
stochastic sampler can outperform the corresponding deterministic ODE sampler.
Read the full abstract ▾
Computer Vision
FlashBack: Knowing When to Remember in Streaming Vision-Language Models
Yi Chen, MingMing Yu, Rui-Qi Wang et al. (+5 more)
Streaming
vision-
language models must process continuously growing
video streams under a bounded compute budget, creating a persistent tension between real-time perception and long-term
memory. Retrieving historical information provides a natural remedy, yet historical recall is not uniformly beneficial: unnecessary history may introduce irrelevant context into current
reasoning and interfere with native real-time perception. Effective streaming
memory should therefore address not only what to remember, but also when and how to access it. To this end, we introduce FlashBack, a training-free framework for selective, multi-level
memory in streaming
vision-
language models. Before retrieving history, FlashBack draws on the semantic understanding of the frozen streaming VLM to infer whether a query calls for historical evidence. This assessment determines whether inference remains on the Native trajectory or invokes an isolated Recall trajectory. The Recall trajectory combines recent context with retrieved long-term
memory through a query-local Side-KV pathway, preserving local temporal continuity without modifying the persistent Native state. We instantiate FlashBack on StreamingVLM and Mage-VL-4B and evaluate it on OVO-Bench and StreamingBench. The results show improvements on several long-horizon and
memory-dependent tasks while largely preserving real-time perception, with performance competitive with strong training-based streaming methods despite requiring no additional training. Our code will be announced later.
Read the full abstract ▾
All authors Yi Chen, MingMing Yu, Rui-Qi Wang, Boran Wang, Xiaohang Cao, Chu Tang, Jingmin Chen, Jie Gu
Computer Vision
Color Independent Word Segmentation From Transcribed Bangla Passages
Faias Satter, Noor Masrur and Sk. Md. Masudul Ahsan
An optical character recognition(OCR) system can scan paper and extract text, making people's jobs easier. While numerous OCR systems are accessible in the software sector, finding a dependable equivalent solution for Bangla is tough. When it comes to handwritten texts, the case is even more rare. The first fundamental step to any OCR is to segment words from text images. If this stage fails, the total OCR's performance will be poor no matter how promising the later stages perform. This research aims to segment words in a handwritten Bangla text image. This research can be implemented on any smartphone-captured image, irrespective of the color and type of paper and ink. Furthermore, as smartphone-captured images can create shadow interferences, the custom
dataset built for this research is created in such a way that every possible obstacle that can be faced is included. For 7374 words, a total of 7278 bounding boxes are generated, which have recall of 90.60%, precision of 91.80%, and F1-score of 91.20%. The system can be further improved with nested operations on bounding boxes containing several words or by adjusting the adaptive thresholding and dilation filter sizes to a more precise level.
Read the full abstract ▾