Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Sunday 4 October

Computation and Language

Towards Unbiased On-Policy Distillation for Block Diffusion Language Models

Zaiquan Yang, Fei Wei, Yong Wang et al. (+6 more)

On-policy distillation (OPD) has emerged as an effective post-training paradigm for language models, with recent efforts extending it to block diffusion language models (BDLMs). However, existing studies focus almost exclusively on small block sizes, leaving distillation into student models with larger blocks underexplored. In this work, we investigate this regime and reveal two critical optimization biases that induce severe training instability. First, mismatched block boundaries between teacher and student cause \textbf{context misalignment}, providing distorted supervisory signals that misguide student decoding. Second, even under aligned contexts, an \textbf{intrinsic optimization bias} in OPD, where the student tends to rapidly absorb high-support signals while lagging on low-support updates, drives a premature confidence surge that traps weaker students in catastrophic overconfidence collapse. To resolve these, we propose \mbox{Un-OPD}, an unbiased on-policy distillation framework with two novelties for stabilizing BDLM training. First, Un-OPD introduces a boundary-aware step filtering strategy that eliminates context-misaligned decoding steps. Second, Un-OPD proposes moderating optimization intensity at high-support positions via a support-rebalanced confidence calibration, thereby bypassing overconfidence collapse. Beyond stability, we also introduce a rollout reuse mechanism to reduce rollout generation overhead. Extensive experiments on math reasoning and code generation benchmarks show that Un-OPD consistently stabilizes training and delivers superior performance while reducing wall-clock training time by approximately half.
Read the full abstract

All authors Zaiquan Yang, Fei Wei, Yong Wang, Yudong Han, Yiyu Li, Zhuofan Zong, Gerhard Petrus Hancke, Xiangxiang Chu, Rynson WH Lau

Machine Learning

Robust Ensemble Guidance for Scientific Inverse Problems

Zixiang Li, Wei Wang, Yunchao Wei et al. (+2 more)

Ensemble guidance combines pretrained diffusion priors with black-box forward models to solve inverse problems without differentiating through the physical simulator. However, observation coordinates with large predictive spread or extreme residuals can dominate the ensemble correction, degrading reconstruction accuracy. We show that two simple modifications, weighting and clipping, substantially improve this correction. Our method, Robust Ensemble Guidance (REG), uses ensemble predictive spread to balance observation scales and adaptively clips standardized residuals to limit the influence of extreme discrepancies. Both operations reuse existing particles and forward predictions, requiring no additional denoiser or forward-model evaluations. Under a local linear Gaussian model, we derive conditions for reduced one-step estimation risk, bound the influence of individual observation coordinates, and characterize when these benefits persist with finite ensembles. Experiments on Navier-Stokes inversion, black-hole imaging, and acoustic full-waveform inversion demonstrate improved reconstruction over the underlying ensemble solver. In particular, REG increases black-hole reconstruction PSNR by 6.2-8.2 dB across three observation regimes and reduces Navier-Stokes reconstruction error by 26.4% in a matched-budget comparison. These findings highlight the importance of observation heterogeneity and residual influence in designing reliable generative solvers for scientific inverse problems.
Read the full abstract

All authors Zixiang Li, Wei Wang, Yunchao Wei, Yao Zhao, Yue Song

Artificial Intelligence

EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans

Xuancheng Li, Beining Wang, Haitao Li et al. (+7 more)

Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing finer-grained evaluation signals. Their effectiveness depends heavily on critique reliability. However, existing GRM training typically uses final preference correctness as outcome supervision. Because the preference outcome space is highly constrained, unreliable critiques can still yield correct outcomes and thus be reinforced. Recent work leverages human critiques for process supervision, but such critiques are scarce and are often reduced to scalar rewards, leaving their fine-grained evaluative information underutilized. We argue that evaluative criteria learned from human critiques can be generalized to broader outcome-only preference data. To this end, we propose EnGRICH, a GRM training framework that pairs the GRM with a training-time MetaCritic learned from a small set of human critiques. MetaCritic constructs response-specific rubrics and uses them to evaluate the evidence coverage and correctness of generated critiques. The resulting signals provide both process rewards for fine-grained credit assignment and structured guidance for exploring better critiques. During GRM training, MetaCritic is further optimized to generalize human-grounded evaluative criteria to outcome-only data. At inference, the trained GRM operates independently. Experiments across seven reward-model benchmarks show that EnGRICH consistently improves over competitive baselines, while further analyses validate the effectiveness of its core mechanisms.
Read the full abstract

All authors Xuancheng Li, Beining Wang, Haitao Li, Heng Wang, Yujia Zhou, Qingyi Pan, Blaze Chen, Yiqun Liu, Min Zhang, Qingyao Ai

Cryptography and Security

AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models

Bao-Phong Nguyen, Gia-Khanh Pham, Thai-Duong Do et al. (+7 more)

The increasing complexity and scale of modern cyber-attacks demand intelligent and computationally efficient Intrusion Detection Systems (IDS). However, designing effective data pre-processing pipelines traditionally involves substantial trial-and-error effort and repeated evaluation of alternative configurations. For large, high-dimensional network traffic data, this process can create a significant computational burden. In this work, we propose AutoDP-LLM, an automated pre-processing framework designed to reduce manual pipeline development and computational overhead. Specifically, AutoDP-LLM leverages Large Language Models (LLMs) to autonomously generate and validate executable data pre-processing pipelines. The framework combines deterministic host-side planning with LLM-based specialist agents to formulate data-processing strategies, synthesize executable code, and adaptively determine retained feature sets using semantic reasoning and training-derived statistical evidence, without requiring a predefined feature budget. Focusing on multiclass intrusion detection, we evaluate AutoDP-LLM on the UNSW-NB15 and NSL-KDD benchmark datasets using multiple downstream classifiers. Comparative experiments against conventional feature-selection methods show that AutoDP-LLM achieves competitive detection performance while automating the generation of compact and executable pre-processing pipelines. Component-level ablation experiments further demonstrate the complementary contributions of the semantic and statistical feature-reduction components. The repeated generation, validation, execution, and assessment of candidate pipelines are amenable to parallel execution, highlighting the potential of scalable computing environments, including high-performance computing (HPC) systems, to support automated IDS pipeline development.
Read the full abstract

All authors Bao-Phong Nguyen, Gia-Khanh Pham, Thai-Duong Do, Mai Xuan Trang, Minh-Tuan Le, Xuan-Nam Tran, Huan Vu, Tien-Cuong Nguyen, Vu-Duc Ngo, Thien Van Luong

Machine Learning

The Effect of Missingness-Pattern Mismatch on Method Selection for Time-Series Classification: A Controlled Empirical Study

Ruiqi Zhao, Zishun Yuan, Zhentao Wang et al. (+3 more)

Classifiers for time-series classification are commonly selected on validation data, but the temporal pattern of missing observations at deployment may differ from the pattern seen during validation. We examine whether such a mismatch affects validation-based classifier selection. In a controlled $2 \times 2$ design, validation and test sets of 64 univariate UCR datasets were masked with either random point missingness or circular block missingness at six rates from 5% to 30%, imputed by linear interpolation, and used to select among three prespecified candidates: 1NN-DTW, MiniRocket with a Ridge classifier, and a statistical-feature Random Forest. Training data remained complete, and selections made under matched and mismatched validation patterns were compared on the same masked test sets. Mismatched validation reduced the test balanced accuracy of the selected classifier by 1.14 percentage points on average (95% CI 0.79 to 1.51), with losses on 49 of the 64 datasets. The loss was negligible at 5% missingness and increased to 2.46 percentage points at 30%. It was concentrated in point-masked deployment (1.84 percentage points), where block-masked validation shifted selection away from the usually best candidate, while the effect for block-masked deployment was small and not significant. Mismatch changed the selected classifier in 35.5% of paired comparisons, but a changed selection did not always reduce performance. A supplementary analysis with non-wrapping linear blocks reproduced these findings with a larger effect (1.67 percentage points). Matching the missingness pattern of validation data to the expected deployment pattern is therefore a simple safeguard for method selection, particularly at higher missingness rates.
Read the full abstract

All authors Ruiqi Zhao, Zishun Yuan, Zhentao Wang, Jiahao Quan, Kangzheng Li, Jianfan Deng

Logic in Computer Science

AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness

Prithwish Jana, Viet Bach Hoang, Logan Luna et al. (+9 more)

Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verification. Despite rapid progress, research-level proofs often depend on concepts missing from leading proof assistant libraries (e.g., Lean's Mathlib), and successful compilation does not guarantee that a translation preserves the theorem's meaning or the proof's reasoning. Furthermore, aligned NL-FL training data are scarce, and leading agents often rely on costly frontier models and manually engineered harnesses. To address the above issues, we present AIProver, an agentic framework for autonomous proof auto-formalization and proof synthesis (AFPS) that jointly post-trains a 119B open-weight language model and evolves its agentic, tool-calling harness with HarnessEvolve. Verifiers assess type correctness, proof completeness, and semantic correctness, returning rewards and diagnostic certificates that drive model fine-tuning and alternating reinforcement learning via symbolic feedback and HarnessEvolve, a certificate-driven evolutionary search over the whole harness control flow that re-tailors the harness to the updated model. For research-level training and evaluation, we introduce LoCoBench, 58.9k instances from Mathlib, CSLib, Mizar Math Library, and a bounded-arithmetic textbook, with a 771-instance validation split whose theorem-proof pairs have no public Lean formalization. Against 39 frameworks spanning AFPS agents, frontier LLMs, and coding agents, AIProver lifts pass@4 semantic correctness over its Leanstral-1.5 base from 15.7% to 36.7% and outperforms every other open-weight system and Aristotle. As a Claude Code and Codex skill, it lifts their semantic correctness from 41.9% and 34.1% to 79.8% and 62.4%, respectively. Further, it is also 24% cheaper than Numina-Lean-Agent, pushing the accuracy-cost frontier of research-level AFPS.
Read the full abstract

All authors Prithwish Jana, Viet Bach Hoang, Logan Luna, Viresh Pati, Akash Singirikonda, Cy Xie, Lisa Carbone, Wuyang Chen, Walter Moreira, Joe Stubbs, Sriram Vishwanath, Vijay Ganesh

Computation and Language

The ÌròyìnSpeech Text Corpus: 24,905 Curated Yorùbá Sentences for Speech and Language Technology

Kola Tubosun, Aanuoluwapo Aremu, Tolulope Ogunremi et al. (+2 more)

ÌròyìnSpeech is a 42-hour, 80-speaker Yorùbá read-speech corpus whose audio has been distributed by ELRA since 2024. This paper describes the release of its text component: 24,905 unique, hand-verified, tone-marked Yorùbá sentences (275,897 tokens; 15,687 types), curated in 2022 as recording prompts. Roughly 11,000 sentences were adapted from openly licensed news material; the remainder were written in-house to broaden coverage beyond the religious translation that dominates existing Yorùbá corpora. Every sentence was checked by hand for tone-mark accuracy, edited for read-aloud clarity and a neutral register, and localised so that non-Yorùbá personal and place names appear in Yorùbá form. Preparing the text for release surfaced systematic Unicode normalisation failures affecting more than 60% of lines (with precomposed and decomposed forms of the same letter co-occurring within single sentences) which we document and correct. The corpus supports diacritic restoration, grapheme-to-phoneme conversion, TTS front-end development and orthographic research, and serves as a validated prompt set for new recording.
Read the full abstract

All authors Kola Tubosun, Aanuoluwapo Aremu, Tolulope Ogunremi, Iroro Orife, David Ifeoluwa Adelani

Information Theory

Modulation and Integration in a local processor having input from two distinct sources

Jim W. Kay and Bruce P. Graham

By making use of partial information decomposition, we analyse information transmission through a local processor which receives two streams of integrated inputs. We revise previously stated conditions for contextual modulation that are based on the components of partial information decomposition, and introduce a condition for the presence of signal integration. Exact results are obtained for information-theoretic measures and the components of partial information decomposition using the Ibroja method. A general class of activation functions is considered along with a particular divisive normalisation transfer function. These results are applied with several activation functions, of additive, multiplicative, subtractive and divisive forms, with graphical illustration, and the conditions for modulation and integration are tested in each case. The revised information-theoretic conditions are also applied to noisy data obtained from a realistic simulation of a model layer 5b pyramidal cell in three distinct regimes defined by experimental design and characterised by the values of the input basal and apical amplitudes. Evidence for driving basal input with modulating apical input, driving apical input with modulating basal input, and of apical-basal signal integration is presented.
Read the full abstract

Robotics

Optimal Control with Learned Critics under Unmodeled State Dependencies

Philipp Schoch and Markus Ryll

Model Predictive Control (MPC) provides a structured and constraint-aware mechanism for decision-making, but its reliance on optimization-friendly analytical dynamics models limits its use in tasks with contacts and other hard-to-model state dependencies. Model-free reinforcement learning avoids explicit modeling assumptions but typically requires large amounts of interaction data. We present a learning-based MPC framework that combines the data efficiency and structure of local model-based planning with learned components that compensate for incomplete dynamics and finite-horizon myopia. The method augments a nominal analytical model with a residual dynamics network that learns missing state-dependent effects from data and combines the resulting planner with a learned action-value critic that injects long-horizon MDP structure into the local iLQR optimization. To make this practical at reinforcement-learning scale, we develop a GPU-accelerated batched iLQR solver that evaluates learned dynamics and critic networks inside the optimal-control loop and solves thousands of trajectory-optimization problems in parallel. The complete system is integrated into a robotics simulator, enabling scalable model-based reinforcement learning under incomplete dynamics. Experiments on biased and incompletely modeled control tasks show that the approach improves closed-loop control performance while preserving the model-based structure needed for efficient constrained trajectory optimization.
Read the full abstract

Human-Computer Interaction

Optimizing AI-Driven Messaging for Type 2 Diabetes Management: Insights from Patient Preference Elicitation

Angela Mastrianni, Defne Levine, Katerina Andreadis et al. (+4 more)

Generative AI (GenAI) allows for improved user experience within conversational agents for diabetes management by supporting dynamic, context-aware conversations. In this study, we elicited patient preferences for the communication style of a GenAI-based conversational agent (uMatter) developed to support diabetes management. We conducted an online survey with 125 individuals with type 2 diabetes. The survey included a discrete choice experiment to evaluate participant preferences for different types of messaging attributes. The survey also elicited participant perceptions and feedback on the messages from uMatter. We found significant preference heterogeneity for the inclusion of emojis within the messages. Additionally, qualitative findings indicated that participants had different desired personas and communication styles for the conversational agent. We propose strategies from recent human-computer interaction and natural language processing research that can be used to design GenAI-based conversational agents that align with the communication preferences of patients.
Read the full abstract

All authors Angela Mastrianni, Defne Levine, Katerina Andreadis, Lynn Xu, Priscilla D'Antico, Antoinette Schoenthaler, Devin Mann

Human-Computer Interaction

Rethinking Inline Citation Verification in Scholarly Communication

Xinrui Fang, Reese Fairchild, Nasi Wang et al. (+4 more)

Inline citations are central to scholarly communication, yet verifying their use is becoming increasingly challenging because of growing review pressures. We conducted a mixed-methods exploratory study to investigate how reviewers verify inline citations, the factors shaping their verification practices, and how they envision GenAI supporting this process. Across interviews (n=12) and a survey (n=203) of reviewers from HCI and AI venues, we found that reviewers' perceptions of citation importance, verification practices, and desired AI autonomy varied across citation types, reviewer characteristics, and research backgrounds. These findings highlight the need for adaptive support tailored to different citation types and reviewer practices, while revealing diverse preferences regarding the use of GenAI for this process. Moreover, effective citation verification should involve collaboration among reviewers, authors, and the broader research community, rather than relying solely on individual reviewers.
Read the full abstract

All authors Xinrui Fang, Reese Fairchild, Nasi Wang, Anran Xu, Simo Hosio, Sylvain Malacria, Koji Yatani

Machine Learning

FACET: Factorized Asymmetric Conditioning for Efficient Transport in High-Fidelity Fluorescence Microscopy Synthesis

Sazan Mahbub, Caleb N. Ellington and Eric P. Xing

Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images from amino-acid sequence and the cell's morphological context enables in silico localization of unimaged proteins. The two conditions, however, play asymmetric roles: morphological context is spatially aligned with the target, whereas sequence is non-spatial and must specify protein-dependent localization within it, with recurring coarse patterns shared across proteins and finer protein-specific variation. Existing generators condition on both jointly, without separating what each explains. We introduce FACET (Factorized Asymmetric Conditioning for Efficient Transport), a probabilistic generative framework that encodes this structure as an explicit inductive bias: sequence semantics are learned from what context leaves unexplained, coarse localization regularities are shared across proteins through a semantic memory, and protein-specific variation is a bounded residual around them. A variance-preserving state projection further lets FACET perform continuous stochastic transport through a pretrained diffusion predictor with minimal parameter overhead. On held-out proteins, FACET improves spatial overlap by 34.3% on the Human Protein Atlas and 14.0% on OpenCell over a backbone-matched baseline, and reduces FID by 27.2% and 46.5%, respectively, with 75% fewer network evaluations. It also substantially improves protein-association structure recovery and yields better-calibrated predictions, while detailed ablations show complementary contributions from its design choices. These results identify factorized asymmetric conditioning, rather than generator capacity alone, as a key lever for high-fidelity, efficient, and biologically meaningful cellular image synthesis.
Read the full abstract

Machine Learning

Rethinking Tabular Foundation Models On Data Streams

Nilesh Verma, Daniel Nowak-Assis, Afonso Lourenço et al. (+4 more)

Tabular foundation models (TFMs) outperform established machine learning models on tabular benchmarks through in-context learning. Building on this success, interest is growing in applying them to data streams, where data arrive continuously and evolve over time. On a stream, a TFM adapts by updating its context rather than its parameters, so its accuracy and cost depend on which examples it keeps and how often it rebuilds its context. We therefore present a systematic study of TFMs on data streams, covering memory management, computational cost, and stream-specific challenges such as concept drift and delayed labels. We find that TFMs achieve the highest predictive performance and that simply retaining the most recent examples is as effective as existing memory management techniques. They also recover faster than streaming learners after drift and keep the highest accuracy under label delay. This accuracy, however, comes at a high serving cost, since a nearly unchanged context is re-encoded at every prediction. These results point to architectural efficiency as the way forward for in-context stream learning.
Read the full abstract

All authors Nilesh Verma, Daniel Nowak-Assis, Afonso Lourenço, Albert Bifet, Bernhard Pfahringer, Maroua Bahri, Nick Jin Sean Lim

Machine Learning

Task Inference Beyond Least Squares in Behavioral Foundation Models

Kuan-Hsun Tu, Chien-Sheng Chiang, Hsin-Wei Chen et al. (+2 more)

Behavioral Foundation Models (BFMs) aim to solve a wide range of downstream tasks without test-time policy learning by inferring a task vector from the reward function. While efficient, the retrieved policies are often suboptimal because of how this task vector is inferred, typically with ordinary least squares (OLS). OLS minimizes reward reconstruction error but leaves the ordering of rewards unconstrained, which can bias the successor measure of the retrieved zero-shot policy away from that of the optimal policy. In this work, we propose BLS, an efficient test-time inference method that balances minimizing reward reconstruction error with reducing successor-measure mismatch. Theoretically, we provide a suboptimality gap upper bound characterized by both successor-measure and reward-function residuals. Empirically, we evaluate BLS on top of state-of-the-art BFMs across benchmarks for locomotion, manipulation, and humanoid control. BLS outperforms existing task inference baselines with negligible computational overhead. Project page: https://embodiedai-ntu.github.io/BLS
Read the full abstract

All authors Kuan-Hsun Tu, Chien-Sheng Chiang, Hsin-Wei Chen, Ping-Chun Hsieh, Tsung-Wei Ke

Computer Vision

Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matching

Kuan-Hsun Tu, Hsuan-Chi Liu, Jia-Wei Liao et al. (+3 more)

We introduce CNP-Flow, a flow matching framework for temporal generation that learns conditional source distributions through flow reversal. Whereas standard conditional flow matching (FM) incorporates conditioning through the vector field and draws source samples from a standard Gaussian, CNP-Flow uses a conditional noise predictor (CNP) to produce an isotropic Gaussian source for each temporal condition. The CNP is supervised by source samples obtained through flow reversal, which maps observed targets backward through a pretrained FM model. A three-stage pipeline pretrains the FM model, trains the CNP, and fine-tunes the FM model using the learned source distribution, while preserving the FM backbone architecture. Across video prediction, video interpolation, and 7-DoF Franka robot motion planning, CNP-Flow consistently improves generation quality. It also matches baseline performance with fewer function evaluations. Project page: https://embodiedai-ntu.github.io/cnpflow
Read the full abstract

All authors Kuan-Hsun Tu, Hsuan-Chi Liu, Jia-Wei Liao, Chien-Sheng Chiang, Cheng-Fu Chou, Tsung-Wei Ke

Information Retrieval

Search Engines Never Say No: How Frozen Agents React When the Retrieval Tool Refuses

Ramraj Chandradevan, Sayontan Ghosh and Vinoth Selvendran

A search tool never says no: it returns its top-k passages even when the index holds no answer, so the agent sees irrelevant text instead of a miss signal. We ask what frozen search agents do when the tool refuses instead. On an index-hole testbed (257 NQ and 300 HotpotQA questions run with and without their gold passages in a 21M-passage BM25 index), seven agents receive one of five refusal wordings. An un-announced one-sentence refusal raises abstention on unanswerable questions from 23% to 97% on average for Qwen3-8B/32B and from 28% to 57% for Claude Haiku 4.5, cutting wrong answers almost one-for-one and beating a system-prompt instruction by 51 points on average. Search-R1 ignores the refusal and fabricates retrievals; Claude Sonnet 5.5 and Opus 5.5 answer from memory (abstention +2 points) and obey a system-prompt directive instead (+16). We also found that wording matters: an explanation beats a bare token; a directive inside the observation is decisive for Haiku; a soft warning is useless. Realistic triggers, from a lightweight score-based predictor to an LLM grounding judge, fall well short of the oracle, and all land on a benefit-versus-signal-quality curve that prices any trigger by its recall at a fixed false-refusal budget: for compliant agents the bottleneck is the detector inside the tool, not the agent, and the curve tells future detector work what each point of recall is worth.
Read the full abstract

Machine Learning

Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks

Emanuele La Malfa, Saar Cohen, Gabriele La Malfa et al. (+4 more)

Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly use mosaic attacks: multi-turn sequences whose individual fragments are innocuous in isolation yet assemble into a harmful payload. We develop a theory of mosaic defense that characterizes what is required to prevent such attacks without sacrificing helpfulness. We first show that no fixed bounded window of recent prompts is sufficient in general: safety-relevant information may occur arbitrarily far back in the interaction. We formalize a watchman, an online state mechanism that carries this information forward, and show that under explicit assumptions it enables zero-failure defense with positive benign helpfulness. Under stronger conditions, it is also optimal among zero-failure defenders. An exact watchman may nevertheless require exponentially many states, while exact maliciousness detection can require exponentially many queries in an unstructured black-box model. These state and query lower bounds do not by themselves imply hard learning: the construction underlying the state lower bound is efficiently learnable from labeled examples, whereas certifying worst-case safety can require substantially more information under restricted access. We also show that self-play equilibrium alone does not certify usefulness, motivating a constrained formulation that maximizes worst-case benign helpfulness among zero-failure defenders. Empirically, training role-specific attacker and defender LoRA adapters over frozen LLMs via multi-turn self-play strengthens both roles: attackers become more effective at eliciting harmful responses, while defenders become more robust to attack, with improvements also observed on unseen attack objectives.
Read the full abstract

All authors Emanuele La Malfa, Saar Cohen, Gabriele La Malfa, Mickel Liu, Christian Schroeder de Witt, Natasha Jaques, Michael J. Wooldridge

Computation and Language

MemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M Reader

Neeraj Yadav

An adequate conversational answer may differ from a short or incomplete benchmark reference. To measure adequacy against the recorded history we prefer source-aware grading, in which the judge checks the reference against the full source before assessing system-blinded answers; original reference-only grading is reported alongside. With a local Qwen 3.8 27B Q4_K_M reader and a 24,000-token evidence ceiling, MemStrata CL1 scores 475/500 (95.0%) on LongMemEval-S and 1,400/1,540 (90.91%) on LoCoMo categories 1-4 under source-aware GPT-5.5 adjudication, against 463/500 (92.6%) and 1,205/1,540 (78.25%) under reference-only grading of the same answers. It preserves a retrieval backbone and adds nonduplicated, dated, speaker-attributed source spans. A same-reader full-history control with about 4.7 times the evidence scores 464/500 reference-only and 470/500 (94.0%) source-aware; neither difference is decisive. Keyword-only selection at the same budget scores 425, and a matched-reader Letta arm 438. On LongMemEval-M, where the packet holds about 1.6% of each history, MemStrata CL1 scores 427/500, with losses concentrated in multi-session and temporal questions. On 300 BEAM-1M questions it outscores dense retrieval, 0.738 to 0.706 (Wilcoxon p = 0.011). A same-seed replay of unchanged requests changed 1.5-2.3% of labels. On identical packets GLM 5.3 flash is non-inferior within 3 points (462 versus 463); Muse Spark 1.3 did not show non-inferiority on 269 questions. None of four pre-registered interventions met all of its registered advancement or feasibility criteria. Signed read-side artifacts support inspection but do not regenerate the private retrieval pipeline. The superiority of source-aware grading to human adjudication is not established, and development exposure, automated-judge dependence and the absence of held-out data preclude an independent-replication or leaderboard claim.
Read the full abstract

Computer Vision

IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning

Jiawen Xi, Yu Zhang, Tianyi Zhao et al. (+3 more)

Infrared small-target detection plays an important role in maritime monitoring and aerial surveillance. Although multimodal large language models (MLLMs) offer promising capabilities for visual understanding, existing MLLM-based approaches struggle to precisely localize infrared small targets. In this paper, we propose IRSTD-Agent, an agentic framework for infrared small target detection through dynamic visual search. The framework enables an MLLM to adaptively determine where and at what scale to inspect an image and progressively gather fine-grained visual evidence for precise target localization. Five complementary visual tools (PROPOSAL, ZOOM, DETECT, DROP and REFINE) support object candidate discovery, adaptive observation, target localization, hypothesis rejection, and target extent refinement, together enabling a coordinated search process over original-resolution images. To teach the MLLMs to conduct this search, we introduce Zoom-guided Interaction Learning, which uses annotation-derived interaction trajectories to supervise tool selection and the corresponding arguments. Through extensive experiments on WideIRSTD-Full and IRSTD-1k datasets, we demonstrate that IRSTD-Agent outperforms the evaluated vision-language models and enhances the precise localization capabilities of MLLMs in IRSTD tasks.
Read the full abstract

All authors Jiawen Xi, Yu Zhang, Tianyi Zhao, Zhu Liu, Maoxun Yuan, Xingxing Wei

Computer Vision

WILLIE: A Unified Framework and Benchmark for Wound Classification, Segmentation, and Localization

Gopi Trinadh Maddikunta, Shannan Hamlin, Hsin-Mei Chen et al. (+2 more)

Chronic wound management affects over 8.2 million patients in the United States and imposes substantial clinical and economic burden. Clinical wound assessment commonly involves three coupled tasks: identifying wound type, delineating wound boundaries, and localizing the wound region for measurement and monitoring. Despite this clinical coupling, existing machine learning approaches typically address wound classification, segmentation, and localization using separate models. We present WILLIE, a unified framework and benchmark for wound classification, segmentation and localization that enables systematic evaluation of multi-task wound analysis under a common protocol. WILLIE harmonizes three public wound datasets into a shared benchmark and compares unified models across three scaling configurations against 10 single-task baselines. The best model achieves 91.88% classification accuracy, 91.41% Dice, and 96.23% AP@0.5 while producing all three outputs in a single forward pass. Beyond aggregate performance, our results show that segmentation-derived localization outperforms dedicated detection baselines in this benchmark, suggesting that box-based localization may be unnecessary for spatially coherent wound targets. Our findings highlight that effective multi-task learning in healthcare imaging depends not only on shared representations, but also on task formulation, compatibility, and benchmark design.
Read the full abstract

All authors Gopi Trinadh Maddikunta, Shannan Hamlin, Hsin-Mei Chen, Kimaya Barnes, Peizhu Qian

Machine Learning

On Semi-Markov Suboptimality in Hierarchical Reinforcement Learning

Bingyun Liu and Yuheng Jing

Hierarchical reinforcement learning uses temporally extended subtasks for exploration, yet committing to their execution can restrict both deployment and policy learning. We identify and separate the resulting execution and policy suboptimality. Task and execution trees distinguish reward objectives from policy choices and decision interruption. A Unified Value Function for HRL and a four-stage Generalized Hierarchical Bellman Equation then support a common analysis of both losses. Under bounded rewards and uniform termination, we establish hierarchical policy and execution improvement results. With the remaining node policies fixed, task-subtree compatibility and node-policy optimality under the original execution mode establish when Markov execution is optimal. The resulting decomposition leads to independent execution choices for behavior, targets, and deployment. We instantiate this principle through execution improvement and one-stage or two-stage policy improvement at arbitrary hierarchy depth. Option-based and goal-conditioned experiments demonstrate complementary gains from changing execution and changing the learning target. Controlled stochastic environments show how these gains depend on stochastic transition strength and spatial structure. This framework makes execution design an explicit component of hierarchical policy optimization.
Read the full abstract

Machine Learning

Green-Routed Neural Operators: Physics Determines Where the Network Reads

Chenhao Si and Ming Yan

We identify a mismatch between the physical role of transport fields in many PDEs and their usual role in neural operators: PDEs use them to select read coordinates, whereas neural operators typically treat them only as input values. We address this mismatch with the Green-Routed Neural Operator (GRNO), which uses the governing equation to determine where latent features are sampled. A parameter-free equation adapter evaluates the diagnostic relation and constructs a departure map whose values are the read coordinates. A multiscale encoder-decoder combines centered and routed reads of latent features to learn the complete finite-time update. Across five two- and three-dimensional PDE systems, GRNO achieves the lowest mean final relative $L^2$ error on four under 40-step autoregressive evaluation and remains competitive on Keller-Segel. Fixed-weight route interventions reveal strong dependence on direction and spatial alignment in four systems, with weak dependence in Keller-Segel. In independently trained ablations, GRNO achieves lower mean errors than variants that supply the transport field only as an input feature, substitute a learned displacement for the equation-specified route, or apply the route with a spatial misalignment, across all five systems. It also substantially outperforms directly advecting the physical state and learning the remaining update, indicating that equation-specified read coordinates provide an effective structural prior for long-horizon PDE forecasting.
Read the full abstract

Sound

SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision

Junyan Jiang, Ruibin Yuan, Jiahao Pan et al. (+4 more)

Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation. Automatically annotated MIDI, rendered into audio, provides scalable supervision across music understanding tasks. Task-specific structured decoders integrate complementary musical cues and their temporal dependencies to produce musically coherent scores. Autoregressive distillation further retains transcription accuracy without task-specific dynamic programming at inference. Across eight benchmark collections, a single SheetSage2-AR model exceeds the listed prior systems on 12 of 15 benchmark–metric pairs in our evaluation, substantially improving over SheetSage1 and surpassing task-specific models on several benchmarks. Model weights and inference code are publicly available.
Read the full abstract

All authors Junyan Jiang, Ruibin Yuan, Jiahao Pan, Wei Xue, Yike Guo, Gus Xia, Yann LeCun

Cryptography and Security

StateSync-GKR: Machine-Checking the Trust Chain from Sparse-Merkle State Transitions to GKR Verification

Jinwook Kim

GKR soundness bounds false output claims about arithmetic circuits, but an application also needs assurance that its circuit encodes the intended state transition. We machine-check this connection for sparse-Merkle membership, non-membership, and update in Isabelle/HOL. A compiler model relates circuit acceptance to transition validity in both directions. A reusable protocol model assembles layer reduction, wiring-predicate extensions, and imported sumcheck soundness into a bound on an explicit chain event. Their composition transfers semantic invalidity to that bound, with the witness fixed before the challenge experiment. Concrete interpretations and premise activations expose vacuous assumption sets that a clean build alone would miss. A further development constructs the exact degree-four KoalaBear extension, lifts the base-field circuit objects, and establishes the assembly bound with denominator $p^4$ under its stated challenge assumptions. An executable Rust prover accompanies the model. Creusot/Why3 contracts provide a partial implementation connection, and a conditional theorem relates successful verifier traces to the model event under an undischarged value-correspondence premise. Neither the transcript's online challenge distribution nor a multi-round Fiat–Shamir reduction is established. The contribution is the composition, within one proof assistant, of compiler correctness with a GKR assembly model, together with an explicit account of the remaining implementation and cryptographic obligations.
Read the full abstract

Artificial Intelligence

AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding

Mahdi Farahbakhsh, Ilan Sela, Fatemeh Doudi et al. (+4 more)

Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role of proposer. The model knows nothing of the search beyond what it is shown. As models grow more capable, a question arises: does a search strategy chosen by a human before the run scale better than promoting the model from proposer to planner and letting it own the search? The Bitter Lesson suggests that choosing the strategy in advance is the kind of hand-designed structure that general methods eventually outscale. We introduce AgentDiscover, in which a coding agent plans the search using its context as working memory, runs experiments, and records every attempt in a database of ideas, candidates, and their relations. This database serves as the agent's long-term memory and is structured so that the selection rules of classical algorithms such as MAP-Elites and Monte Carlo tree search each reduce to a single query, which the agent is free to use, combine, or replace. A server maintains the database and steers the agent after every submission, keeping it on course over long runs. In our experiments, AgentDiscover is more cost-efficient than existing frameworks, reaching better scores at lower cost. On tasks in kernel engineering, biology, algorithm design, and mathematics, AgentDiscover outperforms prior discovery frameworks. Its programs would have placed first among human competitors in seven past AtCoder heuristic contests, and on eleven mathematical and systems optimization tasks it matches or exceeds every baseline that uses the same model. Our code is available at https://github.com/mhdfb/AgentDiscover.
Read the full abstract

All authors Mahdi Farahbakhsh, Ilan Sela, Fatemeh Doudi, Vishnu Teja Kunde, Krishna Narayanan, Jean-Francois Chamberland, Dileep Kalathil

Machine Learning

Diffusion Transformers are Provably Optimal In-context Generators

Guoji Fu, Tomoya Wakayama, Ryotaro Kawata et al. (+3 more)

Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without updating parameters. However, since a few demonstrations cannot uniquely identify the intended task, the challenge is how to learn and sample from an output distribution that reflects this task uncertainty. In this work, we theoretically analyze how a Diffusion Transformer (DiT), pretrained across diverse tasks, learns and generates predictive distributions for a new query from demonstrations. We first show that the natural target to generate from finite demonstrations is not an output derived from estimating a single task, but rather a predictive distribution that captures the task uncertainty remaining after observing the demonstrations. We then prove that a DiT can learn this predictive distribution through score estimation, using attention to aggregate information from demonstrations and diffusion to generate samples. Owing to this property, with sufficient pretraining resources and diffusion sampling steps, the resulting DiT achieves the minimax optimal rate over a Hölder class of test-time tasks. These results imply that DiT acts as a statistically grounded in-context generator capable of generating distributions adapted to new tasks while retaining the uncertainty inherent in finite demonstrations.
Read the full abstract

All authors Guoji Fu, Tomoya Wakayama, Ryotaro Kawata, Atsushi Nitanda, Wee Sun Lee, Taiji Suzuki

Machine Learning

Compact set-valued deep ensembling in multi-class classification

Kim-Dung Tran, Dang-Man Nguyen, Vu-Linh Nguyen et al. (+3 more)

This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and robustness of cautious (set-valued) predictions targeting multiple utilities, which may involve reward-sensitivity. To mitigate the training and storage burdens, we propose to employ compact ensembles, such as Bayesian Neural Networks and Convolutional Neural Networks with the Monte-Carlo dropout prediction option, to produce probabilistic predictions. For each query instance, these probabilistic predictions are then used to define a representative distribution optimizing some statistical distance. The representative distribution is then employed to define the Bayes-optimal prediction (BOP) of any utility. To address the potential unrobustness of singleton prediction making, we propose a family of set-utilities satisfying some desirable properties and whose set-valued BOPs can be found efficiently. Empirical evidence is then given to illustrate the potential (dis)advantages of the proposed ensemble learning framework.
Read the full abstract

All authors Kim-Dung Tran, Dang-Man Nguyen, Vu-Linh Nguyen, Xuan-Truong Hoang, Sébastien Destercke, Van-Nam Huynh

Robotics

VAMPS: Visual and Motor Policies from Sampling-Based Planning

Mohamed Yassine Kabouri, Pietro Noah Crestaz, Quang-Nam Nguyen et al. (+3 more)

Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Motor Policies from Sampling-Based Planning (VAMPS), a framework that uses Model Predictive Path Integral (MPPI) control to train reusable policies without human demonstrations. VAMPS supports two training modes. For one-step proprioceptive policies, it operates iteratively in simulation: the policy warm-starts MPPI, and the refined trajectories provide new supervision as the policy changes. A learned terminal value improves short-horizon planning, while an Implicit Q-Learning (IQL) critic guides the policy update. Iterative refinement outperforms training once on frozen MPPI data, and we transfer the learned locomotion policy to a Unitree Go2. For visuomotor policies, VAMPS operates directly from real-robot data. MPPI uses task-specific state estimates to plan and execute trajectories while recording RGB and sensor observations on a Flexiv Rizon 10S. Action Chunking with Transformers predicts action chunks, reducing the effective prediction horizon, and is trained offline on this fixed dataset. We demonstrate visuomotor pick-and-place and force-aware whiteboard erasing. In the latter task, the policy additionally observes the measured $6$-D wrench and desired normal force. These results show that VAMPS can learn policies either in simulation followed by hardware transfer or directly from autonomously collected real-robot data.
Read the full abstract

All authors Mohamed Yassine Kabouri, Pietro Noah Crestaz, Quang-Nam Nguyen, Qilong Cheng, Ludovic Righetti, Nicolas Mansard

Data Structures and Algorithms

CT-Miner: Fast and Coarse-Grained Time-Series Pattern Mining via Cartesian Trees

Hyundong Jin, Hyunki Hong and Yo-Sub Han

Time series often contain recurring structural patterns, and efficiently mining such patterns into compact representations is essential for scalable analysis of long sequences. Cartesian tree (CT) equivalence provides a well-established structural abstraction that preserves hierarchical order structure while discarding exact values and fine-grained ordinal variations. By grouping multiple ordinal patterns into a shared structural form, CT equivalence offers a principled way to compress recurring temporal structure. However, mining frequent CT-equivalent patterns at scale remains computationally expensive. A naive pairwise approach repeatedly constructs and counts CT representations over subsequences, requiring $O(n^4)$ time for a sequence of length $n$, which severely limits its applicability to long sequences. We propose a new Cartesian pattern mining algorithm based on a Cartesian suffix tree that compactly organizes CT-equivalent subsequences and reuses shared structural information. Our method reduces exhaustive CT-pattern occurrence collection from $O(n^4)$ to $O(n^2)$ time, and we formally prove the correctness and complexity bounds. We further show that this computational gain translates into effective compact representations. Across diverse time-series datasets, a small set of mined CT patterns preserves meaningful clustering structure, and comparisons with finer-grained order-preserving representations show that CT equivalence reduces redundant ordinal distinctions under limited feature budgets. Our implementation is available at https://github.com/hyundong98/CT-Miner .
Read the full abstract

Machine Learning

Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization

Hanzhang Wang, Tianqi Shen, Zonglin Liu et al. (+3 more)

Large language models (LLMs) are typically pretrained in high precision but increasingly deployed with low-precision post-training quantization (PTQ). Recent studies have shown that using weight averaging during pretraining can improve PTQ performance compared with learning-rate decay, suggesting that it might provide a simple way to improve the pretraining-to-quantization transition. But the mechanism behind weight averaging remains insufficiently explained. This leads to inconsistent and fragile performance gains, thereby preventing practitioners from applying such a technique confidently. As a response, we formulate weight averaging as a trade-off between retaining training progress and improving robustness under perturbation. We further derive a continuous family of averaging kernels that unifies conventional strategies and achieves the Pareto frontier between the two competing goals. Critically, a theoretical framework for performing weight averaging under PTQ is developed. It can be shown that coarser quantization is more susceptible to perturbations, whereas finer quantization could be less affected. Thus, our results could provide unified theoretical guidance for performing weight averaging under different PTQ conditions. Experiments validate both the predicted behavior and the proposed averaging strategy. Code is available at https://github.com/MOFA-LAB/weight-averaging-for-ptq.
Read the full abstract

All authors Hanzhang Wang, Tianqi Shen, Zonglin Liu, Junze He, Difan Zou, Ziye Ma