跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 09:10 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 09:55 — 2026-11-10 09:55（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 09:10最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 15,506 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 09:09（北京时间）
新论文 · v1arXiv:2611.01280

Improving Ads Ranking Models with Auxiliary Supervision: Techniques and Insights

Nikhil Bhale, Apurva Pathak, SaiSujithKumarReddy MarapaReddy, Xiao Yin, Prateek Bhansali

原文摘要

Accurate prediction of post-click Conversion Rate (CVR) is essential for personalized ad delivery in the advertising industry. Traditional ads ranking models rely on conversion events (e.g., a user purchasing an item) as ground truth labels for training. However, these conversion events are often sparse or missing, which limits the effectiveness of model learning. The primary contributions of this paper are: (1) a case study on the use of auxiliary supervision from a diverse set of user events and metadata signals beyond traditional conversion events, and (2) advanced modeling techniques designed to maximize the value of these signals. We detail architectural innovations such as linearized labels for improved auxiliary signal precision, a split architecture to facilitate training task decomposition, and a novel Label Combination (LaCo) approach for robustly managing noisy auxiliary data. Empirical results demonstrate that these methods deliver measurable improvements in ranking models, underscoring their versatility and effectiveness across recommendation systems and related domains.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01277

Programmable Droplets as Active Matter in a Reconfigurable Environment

Ivan Shmarov, Abhishek Sharma, Michael Jirasek, Kristine Laws, Leroy Cronin

原文摘要

Exploring systems that bridge the gap between non living and living matter requires a reconfigurable environment coupled to synthetic systems capable of autonomous motion, adaptive behaviour and persistent dynamics. Self propelled droplets provide a minimal platform for such life like behaviour, but quantitative measures capturing both persistence and adaptability to enable closed loop reconfiguration remain lacking. Here we introduce an autonomous closed loop robotic platform to characterise and dynamically program the autonomous behaviour of multicomponent oil in water droplets. We explored two chemical composition spaces, with and without external pH perturbations, analysing droplet behaviour in real time and iteratively selecting formulations. To quantify this behaviour, we introduce two descriptors, persistence and diversity. Persistence is quantified by mapping temporal dynamics in a speed shape complexity space, where we identify a persistence domain that distinguishes active from inactive droplets. Diversity captures spontaneous or environmentally induced variation in motion and the propensity of droplets to reorient or adapt under perturbation. We show that persistence and diversity are constrained by a behavioural trade off: high persistence limits diversity, whereas high diversity reduces persistent activity. Our results provide a quantitative framework for navigating and programming life like behaviours in active droplets and show how closed-loop experimentation can uncover organising principles in complex active matter.

cs.RO · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01276

OntoDoc: Automatically Generating Ontology Resource Descriptions

Juan Guajardo Gutierrez, Mike Tran, Nasim Shirvani Mahdavi, Chengkai Li

原文摘要

Knowledge graphs and ontologies form the backbone of structured, machine-readable knowledge representation, yet ontology terms often lack natural language descriptions, limiting their accessibility and reuse. Existing ontology verbalization approaches tend to rely on rule-based or template-driven techniques that operate on strict, formal schema axioms, resulting in rigid verbalizations that fail to convey richer contextual semantics. We present OntoDoc, a multi-agent framework for automatically generating natural language descriptions for any Internationalized Resource Identifier (IRI) within a SPARQL endpoint or RDF file. OntoDoc operates through a four-stage pipeline: (1) a Database Context agent that adaptively explores the knowledge graph via SPARQL to collect semantically informative triples about the target IRI; (2) a Web Context agent that retrieves and re-ranks encyclopedic background knowledge from Wikipedia and the open web; (3) an Assumption Generation agent that synthesizes both contexts into a structured, evidence-grounded list of intermediate assumptions; and (4) a Description Generation agent that produces the final natural language description from the grounded assumptions. We evaluate OntoDoc on three knowledge graphs spanning biomedical, agricultural, and cross-domain settings, using both automatic scoring via Large Language Models (LLMs) and human evaluation with 11 annotators. OntoDoc consistently matches or exceeds a naive LLM baseline and a template-based ontology verbalizer in accuracy. Furthermore, it vastly outperforms both baselines in the completeness of the generated descriptions, delivering an average 12% improvement in completeness over the naive baseline across all domains, and improving completeness scores by as much as 2.8 points on a 5-point scale relative to the ontology verbalizer.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.09294

Understanding, Predicting, and Steering LLM Behavior via Representational Effective Theory

Muhammed Ustaomeroglu, Guannan Qu

原文摘要

Large language models (LLMs) assist with writing, teaching, programming and decision-making, yet the computations underlying their behaviour remain largely opaque. Full access to every weight and activation does not by itself yield understanding: a microscopic description need not reveal how computation is organized at the level that governs behaviour. Complex systems are often understood instead through a few macroscopic variables whose dynamics capture the behaviour of interest, as temperature and pressure do for molecular motion in thermodynamics. Here we show that such an effective description of LLM computation can be learned directly from data. We introduce Representational Effective Theory (RET), a framework that learns low-dimensional macrostates and their dynamics from a model's hidden-state trajectories. These macrostates exhibit approximately closed dynamics and trace interpretable trajectories through reasoning. They also predict sycophancy and alignment faking early in generation, while steering the model towards selected macrostates produces corresponding changes in its reasoning. Together, these results show that LLM computation admits useful macroscopic descriptions that support interpretation, prediction and control.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01272

Geometry of Confabulation and Refusal in Small Language Models

Vladimir Kazei

原文摘要

Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer. Can the hidden state before the first generated token provide a clue? Can we flip confabulations into refusals? I introduce ConfabQA, a 784-item benchmark whose obscure-pre-cutoff category breaks the typical correctness/knowledge-cutoff confound and map the geometry of the hidden state with linear probes, a sparse autoencoder (SAE), and direct optimization of intervention directions. On Qwen3-1.7B and Gemma 2 2B the probe separates upcoming refusals from confabulations well beyond prompt features (+7.4/+16.3 pp); on Llama 3.2 3B the ConfabQA margin is within fold-to-fold spread, but a direct refusal probe on PopQA and TriviaQA recovers +18-25 pp. On Qwen I closely inspect three candidate directions for the refusal vector: probe-recovered, Qwen-Scope SAE feature, and directly optimized. Although the three directions are pairwise 50-81 degrees apart, a push at or below the state's own norm along any of them flips most confabulations into refusal openings dominated by the "As..." family. Forcing the opener without touching the hidden state yields the same one-in-three judged-refusal rate as any push. The opposite push collapses refusals mostly into confabulations, yet leaves originally correct answers intact, so the direction gates the opening speech act rather than the knowledge behind it. Confabulations do not resolve into a concentrated feature in a dictionary or a token signature on Qwen3-1.7B. Scoring every probe on the margin over the strongest of four prompt-feature baselines extracts the hidden state's own contribution. Correctness signal is model-dependent and portable only for Llama 3.2 3B: 81% of the probe's margin over test majority survives transfer between ConfabQA, PopQA, and TriviaQA. Benchmark, judge, and code are released.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.08683

Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio

Phillip Long, Zachary Novack, Chris Donahue

原文摘要

Autoregressive "language" models (LMs) trained on raw waveforms can be repurposed for lossless audio compression, but prior work is limited to 8-bit audio, leaving open whether such approaches work for practical settings (16/24-bit) and can compete with existing codecs. We benchmark LM-based compression on full-fidelity audio across diverse domains (music, speech, bioacoustics), sampling rates (16kHz-48kHz), and bit depths (8, 16, 24-bit). Standard sample-level tokenization becomes intractable at higher bit depths due to vocabulary size (65K for 16-bit; 16.7M for 24-bit). We propose Trilobyte, a byte-level tokenization schema for full resolution audio, improving vocabulary scaling from $O(2^{b})$ to $O(1)$ and enabling the first tractable 24-bit LM-based lossless compression. While LMs consistently outperform FLAC and yield state-of-the-art compression at 8-bit and 16-bit, we observe that compression gains become more modest as bit depth increases beyond 8-bit.

cs.SD · cs.AI · cs.LG · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38691

Beyond fabrication: Misattributed numbers in papers written by AI research agents

Mosab Alfaqeeh, Omar Mohammed Horani, Mou'th Hourani, Hashem Alfaqeeh

原文摘要

Verifying numerical claims in research written by AI agents is an important but challenging problem. Recent benchmarks show that many agent-written papers fail integrity checks, but such verdicts, often produced by a single LLM judge, identify failure without explaining its nature, and existing checks either test a paper for internal consistency or test whether a reported value appears somewhere in an agent's output. We re-analyze all 540 released judgments from a recent public benchmark of AI research agents (nine agents, fifteen open research problems) and manually label 256 numerical claims from 18 submissions. Failures concentrate on alignment between the paper and the underlying work rather than overt cheating, and about four in five unsupported claims correspond to values in the agent's own files that come from the wrong experiment, metric, or run. We introduce a deterministic claim-to-evidence checker that scores whether the surrounding context identifies the claimed result and calibrates each claim against numerical decoys. With its rules fixed before labeling, it certifies claims with over 90% precision against blinded annotators (78 of 85; Cohen's kappa = 0.89), while verifying only a subset of claims; most claims it cannot verify are nevertheless traceable, so failure to verify is not evidence of falsehood. An LLM verifier given the same evidence recovers more traceable claims but accepts about three times as many misattributed ones, so the two are best used together. Applied to 99 submissions, the checker reveals large differences in traceability across agents, and on 30 submissions a second judge configuration, with a different model and harness, orders the agents' vendor groups as the official judge does while passing twice as many papers. These findings motivate provenance-first auditing of AI-produced research.

cs.AI · cs.CL · cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01269

Learning momenta for Hamiltonian-based models

Ignacio Puiggros T., A. Srikantha Phani

原文摘要

There has been increasing interest in methodologies that incorporate physics priors into neural network architectures to enhance their modeling capabilities. Among these methodologies, Hamiltonian neural networks (HNNs) and their variants have gained considerable attention. These architectures explicitly encode Hamiltonian mechanics both in their structure and loss function, resulting in desirable properties and additional modeled information. A crucial limitation of HNNs is their reliance on data on the target system's generalized momenta. This severely hampers their applicability when the analytical form of the generalized momenta is unknown, which frequently is the case in real-world applications. The goal of the present work is to develop a general extension of Hamiltonian-based architectures that addresses this issue by simultaneously learning the system's generalized momenta, Hamiltonian structure, and dynamics from data. The proposed architecture learns the generalized momenta when their analytical form is unknown, and only (potentially non-sequential) data on the state and its derivatives is available. A dissipative mass-spring system, a double pendulum, and a rolling disk under nonholonomic constraints are considered as canonical examples to assess the performance of the proposed architecture.

cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01268

EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching

Injy Hamed, Adarsh Arigala, Rufael Marew, Arjun Gangwar, Atharva Kulkarni, Hanan Aldarmaki, Srinivasan Umesh

原文摘要

Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology. In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation preservation. We then train an Arabic-centric model based on EZ-VC on diverse Arabic speech, and demonstrate strong performance in intelligibility, naturalness, and pronunciation preservation, while maintaining high speaker dissimilarity. Through subjective evaluation, we further demonstrate its robustness to code-switching and cross-dialectal conversion, as well as its generalization to Arabic dialects with limited representation in the training data. Our findings highlight the limitations of zero-shot VC and the importance of target-language adaptation for robust voice anonymization.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01265

Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts

Heeyong Eun, Seungyeon Chung, Hyejee Park, Youngeun Lee, Sukhyun Hong, Hyewon Jung

原文摘要

As coding agents gain greater autonomy to modify software repositories, relevant context alone does not define their operational authority. An artifact may be relevant to a maintenance task while being inappropriate to edit; conversely, another artifact may be required even when it is not explicitly mentioned in the request. We explore Boundary Contracts, a machine-readable abstraction that makes task-specific artifact roles (editable, inspect-only, required, and protected) explicit before repository modification begins. We conduct a pilot study on 40 maintenance tasks from a real enterprise repository, comparing the same Codex-based coding agent with and without Boundary Contract information. The boundary-informed condition improves macro edit-selection F1 from 0.440 to 0.682, required-behavior coverage from 0.429 to 0.673, and the number of strictly acceptable patches from 9 of 40 to 18 of 40. To probe whether these gains are explained only by improved file localization, we additionally analyze 21 tasks in which both conditions modify at least one identical file. Differences remain in edit selectivity and patch outcomes, providing initial evidence that explicit artifact roles may influence maintenance behavior beyond localization alone. This pilot does not establish the general effectiveness of Boundary Contracts. Rather, it provides initial evidence for a broader research question: how should the operational boundaries of coding agents be generated, validated, revised, and ultimately enforced as repository-level maintenance becomes increasingly autonomous?

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01263

StreamClarify: Proactive Clarification for Grounded Streaming Video Question Answering

Zhuchen Shao, Bo Chen, Klara Nahrstedt

原文摘要

Streaming video question answering (QA) requires real-time reasoning over continuous video streams under strict latency and active-context budgets. Current streaming vision-language models (VLMs) often give confident yet ungrounded answers when queries are ambiguous or have false premises, or when relevant visual evidence is no longer in the active context. Proactive clarification can help, but must satisfy the same latency and memory constraints. We present StreamClarify, a training-free framework for grounded streaming QA that combines a pre-answer uncertainty check with hierarchical memory. The check uses the entropy of a binary pre-answer judgment as a lightweight uncertainty score to decide whether to answer directly or request clarification. To support re-answering, a temporal-pyramid KV cache maintains a bounded active visual context, while a CPU-side semantic retrieval archive provides access to historical frames. We further construct StreamClarify-QA, a diagnostic benchmark of 1,837 QA pairs from StreamBench and OVO-Bench, spanning standard, referential ambiguity, and unanswerable scenarios. Across three VLM backbones, StreamClarify improves Macro accuracy by up to 8.2 points over backbone-matched baselines. At comparable trigger rates, entropy-based selection achieves more than 18 points higher precision than random selection in identifying initially incorrect answers. Under oracle user guidance, clarification improves Macro accuracy by up to 3.5 points. We also report a controlled, oracle-assisted Qwen3-VL simulation on Ambiguous QA with generated questions and referent-only user replies, where the entropy-gated condition improves accuracy by 8.3 points.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01262

Does Random Search Discover Task Experts? Revisiting Neural Thickets

Julian Asilis, Guanzhe Hong, Vatsal Sharan

原文摘要

Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise. Gan & Isola (2026) recently proposed a striking alternative: that pretrained models lie in a dense neural thicket of task specialists, which can be surfaced with simple Gaussian weight perturbations. We examine this neural thicket of task-specific experts and identify several key findings that question this perspective. First, we find that the apparent lift of the best-of-N selected perturbation decays quickly with selection-set size m, strongly suggesting overfitting to the selection questions. In fact, for 10 of the 12 model-task pairs we study, a simple null model of pure selection noise predicts more than 75 percent of the top expert's reward lift. Second, the top experts' advantage often vanishes on held-out questions or remains within the run-to-run variability of the unperturbed pretrained model. Third, we find that majority voting over the top-K selected perturbations, termed RandOpt(N, K) by Gan & Isola (2026), is often matched or outperformed by majority voting over K samples from the base model. Overall, our results suggest that random weight perturbations may be ineffective at uncovering task experts around pretrained models, and that task adaptation requires more sophistication than random search. Code and artifacts are available at github.com/asil012/RevisitingNeuralThickets.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01261

MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA

Elahe Khatibi, Ziyu Wang, Amir M. Rahmani

原文摘要

Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into a frozen E5 text embedding space. This enables a dense retrieval path that accepts a waveform without a query transcript. Retrieved passages and speech-linked textual metadata support answer generation with entity alternatives, diagnostic contrasts, relation heuristics, and bounded retrieval refinement. ASR-less refers to the initial speech retrieval interface; lexical retrieval, string-based entity correction, and the text generator require textual inputs. The deterministic speech embedding does not constitute a calibrated model of acoustic uncertainty. Reported retrieval results reach 87.6 Recall@10 for the speech-only retriever and 90.4 for the hybrid configuration, compared with 81.0 for transcript-first dense retrieval. Medical QA and ablations provide descriptive system comparisons, with input-provenance and evaluation limitations stated explicitly. We distinguish controlled synthetic acoustic tests from real clinical speech, qualify component attribution, and specify the remaining comparisons needed to assess speech-only QA and clinical generalization.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01256

LoRAForge: Co-Designing Post-Hoc Compression and Execution for Efficient Multi-LoRA Serving

Shenghui Li, Thiemo Voigt

原文摘要

Multi-LoRA serving allows many task-specific adapters to share a common base model, but scaling to large adapter fleets introduces substantial storage, loading, and execution overheads. Post-hoc compression can reduce the memory footprint of trained LoRA adapters, yet smaller ranks do not automatically translate into faster serving. For instance, padding, factor access, and generic kernels can obscure the retained low-rank structure, while independently recompressing thousands of modules also incurs significant preparation overhead. We present LoRAForge, a system connecting batched factor construction to rank-specialized execution through an explicit retained-rank representation. It supports two allocation policies: uniform retention ratios (LoRAForge-U) and spectral-energy budget allocation (LoRAForge-S). Both share FlashTSQR factor construction and the same serving backend. FlashTSQR exploits parallelism across modules and row tiles, accelerating factor construction by up to $2.28\times$ over matched library QR. In a fixed-work Qwen control, the shared runtime adds $1.17$--$1.22\times$ throughput across both compressed policies, with negligible gains on original adapters. Across 85 trained open-weighted Qwen and Llama adapters, the spectral policy's floored quality configuration retains about 7.7% of adapter parameters with fleet-average score drops of at most 1.2 points on a 0--100 scale. The same rank-floored $1/12$ spectral exports achieve substantial token-throughput gains on both AMD and NVIDIA GPUs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01252

Context-Shielded Backdoor Attack against Large Vision-Language Models

Zhifang Zhang, Qiang Huang, Chenpeng Wang, Weitong Chen, Olaf Maennel, Wei Emma Zhang, Lei Feng, Lei Zhang 等 9 位作者

原文摘要

Large vision-language models (LVLMs) routinely use inference-time visual-token compression to prune hundreds of patch tokens down to a compact budget. Existing LVLM backdoors fire whenever a triggered image appears, whereas prior deployment-triggered attacks activate only when model weights are quantized or pruned. However, conventional LVLM backdoors exhibit nearly 100% attack success rate (ASR) under full-token inference, immediately exposing compromised checkpoints during pre-deployment auditing. We reveal context stripping: surrounding clean visual tokens suppress an embedded trigger at full length, whereas token pruning strips this context away and activates the backdoor. Motivated by this finding, we propose StripWake, a projector-only backdoor that remains dormant under full-token auditing yet activates across unseen compressors. Specifically, StripWake pairs clean-supervised full-token views with target-supervised randomized compressed views, and aligns early visual attention with a frozen benign teacher to preserve clean utility. On LLaVA-1.5-7B across nine unseen compressors, StripWake stays dormant at 0.4% full-token ASR yet achieves 94.0%-99.7% compressed ASR across five primary compressors without CIDEr loss.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01250

Shades of Success: Evaluating Manipulation Quality from Object-Centric Constraints

Lorena Maria Genua, Sarvesh Prajapati, Ananya Trivedi, Taskin Padir

原文摘要

As learned manipulation policies become increasingly capable of solving practical manipulation tasks, assessing how well a task is performed becomes a fundamental challenge. While binary labels confirm task success, they cannot distinguish successful executions with different levels of geometric precision. To address this, we introduce SPECTRA, an object-centric framework for quantifying execution quality in manipulation of rigid objects. From a small set of oracle demonstrations generated in simulation, SPECTRA represents object interactions through progress-aligned relative poses. SPECTRA identifies which relative-pose directions are constrained and their admissible variations from demonstrations. These constraints establish a reference for evaluating robotic manipulation tasks. To score an unseen execution, deviations beyond the admissible variation are summarized by a Task Quality Index Q in [0,1]. Across seven simulated tasks, SPECTRA recovers constraints with 94% accuracy using 30 demonstrations per task. On rollouts from three learned policies, its scores achieve pooled Spearman correlations with human judgments of p=0.81 over all rollouts and p=0.61 among successful rollouts, exceeding all baselines in both subsets. Using the task reference learned in simulation, we use SPECTRA to select the highest-scoring demonstrations for training a diffusion policy on hardware. Exploratory results show higher success rate than training on randomly selected demonstrations.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2510.25069

TOPol: Reconstructing and Interpreting Multidimensional Semantic Polarity Fields

Lucia Gomez, Gabin Taibi, Julius Sipke Kooistra

原文摘要

Polarity in natural language processing has long been operationalized as a single axis: the sentiment construct. We challenge this one-dimensional view by asking what a topic's documents are bipolar about, without specifying an answer in advance. TOPol inverts the usual concept-direction paradigm: rather than mapping a named construct to one direction, it maps a topic to the full set of statistically reproducible bipolar semantic axes its documents support in a transformer's residual stream, and asks only afterwards which of them correspond to a known construct. These axes need not be evaluative. The method is a recursive, orthogonal-by-construction bipartition of each topic's document cloud, with a candidate axis promoted to a finding only if it survives one pre-specified split-half stability gate. We calibrate against a known answer first: on 9,986 Amazon reviews (14 discovered topics) in Gemma 3 4B, the star-rating difference-in-means vector serves as a ruler known by construction to be sentiment. Discovery blindly re-derives the sentiment axis in every topic (cosine 0.71-0.97) without ever seeing the rating label, while the same gate certifies 543 axes, of which 106 are near-orthogonal to sentiment yet equally reproducible; each topic supports 33-45 mutually orthogonal axes, and sentiment axes resolve in later layers than the rest. Differential vocabulary, an internals-grounded natural-language decoder and vocabulary-based clustering agree on what the non-sentiment axes contrast; clustering by shared vocabulary surfaces 99 families, 9 recurring across topics. Direction similarity to the ruler predicts an independent sentiment estimate only weakly ($r=0.243$). Polarity is better treated as a property of a topic's representational geometry, with a measurable rank and a per-axis depth, than as one universal scalar.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.07746

Flow Matching for Count Data

Ganchao Wei, John Pearson

原文摘要

High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mappings between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based deep generative models for images, video, and text motivates extending these ideas to count-valued settings, but many existing methods either treat each count as a categorical state or transform counts into a continuous space, neither of which is natural or efficient when the count range is large. We propose count-FM, a flow-matching framework for count data based on a continuous-time birth-death process with local unit jumps. Count-FM learns marginal transitions efficiently in count space through simulation-free training of conditional transition rates, allowing transport between arbitrary count-distributed source and target populations. In simulation, count-FM variants achieve strong sample quality while using substantially fewer parameters. We further apply count-FM to scRNA-seq and neural spike-train data for unconditional generation, transport, and conditional generation. Across these tasks, count-FM yields improved sample quality, greater modeling efficiency, and interpretable transport paths.

stat.ML · cs.LG · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01245

Learning What to Ask and What to Believe: Distilling a Variational Bayesian Agent into Language Models

Baichuan Li, Yanling Chang, Alfredo Garcia

原文摘要

Interactive tasks such as eliciting a user's preferences or diagnosing a hidden mechanism require an agent to track its uncertainty over a latent state, ask informative questions and act on the answers. Language models have no explicit mechanism for this, whereas Bayesian information seeking provides one through posterior inference and expected information gain (EIG), and we ask whether it can be distilled into an 8B language model. Our teacher, a lightweight Bayesian agent with a sequential variational belief and EIG query selection, matches or approaches exact and particle references on three task families. We generate synthetic interactions with the teacher on episodes disjoint from the benchmark and fine-tune \Student{} to reproduce its queries and its belief state as a structured scratchpad. On three Multi-Turn Puzzles tasks the student raises Circuit Decoding from 0.00 to 0.93 success, lowers the normalized rank of the recommended film from 0.50 to 0.10 and cuts word guessing from 32 to 3.4 attempts, exceeding the strongest reported language models on the two comparable tasks. Exposing the belief state closes much of the gap where the decision is an implicit computation rather than a read-out of the interaction; in matched teacher contrasts, EIG supervision consistently outperforms random querying, whereas greater inference fidelity does not uniformly improve the distilled student; a 70B language-model teacher does not match the Bayesian teacher in downstream student performance, and the learned skill does not transfer to an unseen task family. Variational Bayesian information seeking can thus be amortized into a language model by transferring the belief state that drives its questions and decisions.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.26236

DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation

Ferdinand Paar, Lanmiao Liu, Aslı Özyürek, Serge Thill, Esam Ghaleb

原文摘要

Co-speech gesture generation requires both semantic expressivity and biomechanically plausible rhythmic motion. Existing holistic gesture models mix lexically grounded semantic gestures with frequent prosody-aligned beat gestures. This limits semantic grounding, speech-motion alignment, and kinematic smoothness. We propose DuoGesture, a neuro-inspired and biomechanically informed approach that decomposes co-speech gesture synthesis into semantic and beat streams. The two streams are coordinated by a Semantic Variational Information Bottleneck, a stochastic frame-level gate that learns when semantic gestures should override rhythmic beat motion. The semantic stream is controlled by Motion-Grounded Semantic Conditioning, which replaces purely linguistic word embeddings with motion-language representations to provide motion-aligned semantic priors for long-tailed lexical triggers of gestures. The beat stream is further regularised by an Inertial Beat Prior, an anthropometry-weighted arm-chain module that reduces jitter and improves rhythmic consistency without constraining semantic frames. Objective evaluations and subjective experiments show that DuoGesture outperforms strong baselines, while component ablations confirm the complementary roles of semantic grounding, stochastic stream selection, and biomechanical regularisation. We encourage readers to view our demos and qualitative illustrations, which are available on the project page: https://ferdinandpaar.github.io/DuoGesture/.

cs.CV · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.01691

Can MLLMs Perceive and Describe Medical Image Quality Beyond Scores?

Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Jiafan Zhang 等 19 位作者

原文摘要

Medical Image Quality Assessment (IQA) serves as a critical safety gate for clinical AI, yet existing approaches rely on scalar metrics that fail to capture the descriptive, expert-like evaluation process central to clinical practice. We introduce MedQ-Bench, a comprehensive benchmark for language-based medical IQA evaluation with MLLMs, establishing a perception--description paradigm across 5 imaging modalities and over 40 quality attributes. The benchmark comprises two complementary tasks: MedQ-Perception probes low-level visual attribute discrimination via 2,600 expert-annotated perceptual queries; MedQ-Description covers both no-reference and comparison description sub-tasks with 708 expert-annotated samples, evaluated through a four-dimensional judging protocol. Comprehensive evaluation of 23 state-of-the-art MLLMs reveals that current models exhibit only preliminary and unstable capabilities, and highlights the urgent need for targeted optimization of MLLMs in medical IQA. Project & Dataset: https://github.com/liujiyaoFDU/MedQ-Bench

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01239

Mathematical Formulation and Comparative Performance Evaluation of Machine Learning Algorithms for Maize Land Suitability Prediction

Haimanot Bitew, Ayisheshim Almaw, Habtamu Zegeye, Demeke Alene

原文摘要

Addressing the food needs of a growing population is one of the major challenges of developing countries like Ethiopia. Various policies aimed at increasing food production have been enacted by governments and development partners. Although efforts in this regard have been made, there is still inadequate emphasis on increasing food production through the use of high technology practices. Precision agriculture using technology has been utilized to increase crop yield. Precision agriculture also relies on identifying land for a crop, which is a key factor that affects crop yield. Traditional methods of assessing land suitability for crop production are time-consuming, costly and unreliable. Against this background, the aim of this study was to assess the potential of machine learning (ML) in improving the speed and accuracy of assessing land suitability for maize, a staple crop in Ethiopia, as compared to traditional methods. The study is investigated in three areas (Burie, Shindi and Tilili) in the Amhara region. Data collection was done through the local agriculture offices and survey teams. The data were coded, scaled and balanced. Various feature extraction techniques, which included Univariate Feature Selection(UFS), Recursive Feature Elimination with Cross-Validation(RFECV) and Sequential Feature Selection(SFS), and various classifiers, which were K-nearest neighbor (KNN), gradient boosting (GB),random forest (RF) with mathematical formulations were employed. The best models were constructed through combining GBOOST and SFS and achieved an accuracy of 99.41% and 99.35% for both precision and recall. Our results showed that using machine learning is a reliable method of assessing land suitability for maize in Ethiopia. Keywords: Maize, Gradient boosting,Land suitability,Machine learning, Mathematical formulations

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01234

How Much Can Approximate Equilibria Change the Social Cost of Selfish Routing?

Yu Cheng, Tianle Jiang

原文摘要

We study approximate Nash equilibria in nonatomic congestion games, with the goal of understanding how much the social cost can change when the equilibrium condition is relaxed. We consider $ε$-approximate Nash equilibria ($ε$-NE), in which each player uses a strategy whose cost is at most $1 + ε$ times the minimum available cost. We compare the social costs of $ε$-NE and exact Nash equilibria. This lets us quantify, for example, how much a navigation app can reduce total travel time when drivers tolerate routes slightly slower than the fastest available route. For degree-$d$ polynomial latencies in both general nonatomic congestion games and single-commodity routing games on series-parallel networks, we give tight lower and upper bounds on the relative change in social cost from an exact Nash equilibrium to any $ε$-NE, with matching instances for every $ε$. For small $ε$, the largest possible relative reduction and increase in general congestion games are both $Θ(\sqrt{dε})$, independently of the number of resources and populations. In contrast, on series-parallel networks of depth $h$, the largest possible relative reduction is $Θ(hε)$, while the largest possible relative increase is known to be $ε$. For the classes of games we study, these results give a tight and quantitative characterization of the possible changes in social cost and establish a separation between general and series-parallel networks.

cs.GT · cs.AI · cs.DS · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01233

STLT: A Novel System for Energy-Aware Distributed Inference in the Edge-Cloud-Space Continuum

Andrija Stanisic, Milos Gravara, Juan Luis Herrera, Stefan Nastic

原文摘要

Low Earth Orbit satellites are pivotal for Earth observation tasks such as wildfire detection, capturing imagery for analysis by Deep Neural Networks (DNNs). On-board analysis reduces downlink volume, but severe energy constraints force a trade-off between computation and data transmission. Splitting the DNN between satellite and ground turns this balance into a design choice, where the split point determines combined computation and downlink energy. Existing approaches typically rely on static split-point decisions that fail to account for dynamic space conditions, or on complex algorithms, historical data, or prediction models that introduce significant overhead. To address these shortcomings, we present STLT, a two-stage system for energy-aware distributed inference between LEO satellites and a ground station. First, an offline analyzer characterizes the DNN architecture to identify a set of favorable split points, consequently reducing the search space. Second, an on-board algorithm performs lightweight energy-aware split selection, dynamically choosing from this pre-computed set based on the current state of the environment. We evaluate STLT on a real-world satellite telemetry dataset, showing that it reduces the split-candidate search space by 30.7% on average, lowers decision latency by 25.1% and energy by 27.5% on average, and delivers up to 20.1% more inference tasks than a state-of-the-art satellite-ground co-inference baseline while consuming 8.8% less energy overall.

cs.DC · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01230

Reproducing INP-Former: Reconstructing Intrinsic Normal Prototypes for Industrial Anomaly Detection

Yunfei Liang, Juan Pablo Osorio Rivera

原文摘要

We reproduce the central claims of INP-Former, a reconstruction-based method for multi-class industrial anomaly detection. INP-Former extracts Intrinsic Normal Prototypes (INPs) from each test image and uses them to guide a decoder that reconstructs normal features, without a stored memory bank. Using the authors' released code, we reproduce the reported performance on MVTec AD and VisA and extend the evaluation to MVTec AD 2, where image AUROC with the default settings is 63.4, compared with 99.7 on MVTec AD. On MVTec AD, a five-seed ablation shows that most of the performance comes from the INP mechanism, while the two auxiliary losses add small changes whose direction depends on the metric. A paired comparison with both losses disabled confirms the benefit of INP on MVTec AD 2. The default of six prototypes transfers less well: the plateau beyond four prototypes reproduces on MVTec AD and VisA, but on MVTec AD 2 a single prototype outperforms six in AU-PRO on the public split and on both hidden test splits. We also measure practical trade-offs in resolution, backbone size, training length, and LoRA adaptation, and examine performance by defect size, lighting condition, and a stricter AU-PRO limit. Several conclusions from the original benchmarks, including the default prototype count, do not carry over to harder data. Code: https://github.com/garasnote/Repro-INPFormer

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01222

Modeling Fat-shift for Improved Head Segmentation from MRI Scans using a Probabilistic Model

Merle Diedrichsen, Koen Van Leemput, Douglas N. Greve, Oula Puonti, Axel Thielscher

原文摘要

Personalized computational head models for biophysical simulations rely on accurate whole-head segmentations from T1-weighted (T1w) magnetic resonance imaging (MRI) scans. While T1w scans provide excellent contrast for intracranial anatomy, extracerebral tissues have partly almost no signal (compact bone) and also suffer from the so-called chemical shift artifact, which affects the fatty tissues in MRI and causes them to spatially shift in the frequency encoding direction of the scan. This artifact occurs primarily in two structures of the head: the spongy bone, a fatty compartment inside the compact bone, and the subcutaneous fat, located directly underneath the skin. The frequency-encoding direction is often set in the superior-inferior direction, causing the fatty tissues to shift down and, as a result, making the skull appear thinner than it actually is. Existing segmentation methods do not model this artifact, consequently leading to inaccurate labeling of the skull and scalp, which introduces a bias in biophysical simulations. The direction and magnitude of the fat-shift can be determined from the scan parameters, thus making it possible to explicitly model the shift and to recover the correct anatomy. This study introduces a probabilistic model that uses variational inference to segment head and brain structures from a T1w scan while accounting for the fat-shift artifact. The proposed Fat-shift-informed Label Optimization of the Whole head (FLOW) method reconstructs extracerebral anatomy more accurately than a fat-shift-agnostic segmentation approach while maintaining high segmentation accuracy in all other structures. FLOW-based fat-shift corrected segmentations significantly reduce bias in electric field simulations compared to a segmentation method that does not model the shift.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.06445

A Survey on Agentic Security: Applications, Threats and Defenses

Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed, Farig Sadeque, Md Rizwan Parvez

原文摘要

In this work we present the first holistic survey of the agentic security landscape, structuring the field around the fundamental pillars of Applications, Threats and Defenses. We provide a comprehensive taxonomy of 274 papers that covers red-teaming, blue-teaming and domain-specific applications, attack surfaces on agentic systems, defense techniques, and both offensive and defensive evaluation frameworks. For each pillar, we first discuss the literature around the taxonomy and then perform a quantitative analysis to understand the patterns across these works. For the applications, we show their security-lifecycle coverage map, compare between red-teaming and blue-teaming agents, and analyze the adversarial use of red-teaming applications. On the threat side, we analyze the entry points and agent-loop stages that attacks target, their specificity to the agentic setting, and the threat models they assume. On the defense side, we analyze the prevailing defense strategies, their cost and security trade-offs, and where in the agent lifecycle they are deployed. Finally, we provide a deatiled cross-cutting analysis, where we map which defenses cover which attack classes and chart trends in agent architecture, backbone model usage, and data modality coverage. Taken together, these findings give a researcher a structural understanding of how agentic capabilities, vulnerabilities, and countermeasures relate to one another, and to identify where the field is concentrated and where it is thin.

cs.CL · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01220

Differentiable Iterative Learning Control for Black-Box Position-Commanded Manipulators

Mohammed Al-Ghaili, Yakoop Qasim, Hassan Almubarak

原文摘要

High-accuracy repetitive tracking is challenging for position-commanded manipulators whose low-level controllers are inaccessible, while constrained model-based iterative learning control (ILC) can require substantial manual parameter tuning. We present Differentiable Iterative Learning Control (Diff-ILC), an online bilevel framework that adapts the parameters of a constrained ILC update between physical robot executions. A closed-loop differential model is identified once from paired smooth perturbations and subsequently kept fixed. At each trial, a constrained quadratic program computes a feasible command correction, while a real-anchored next-trial prediction defines a task-level objective. Hypergradients are obtained by implicitly differentiating the locally active KKT system, enabling multiple computational parameter updates without additional robot executions. Experiments on a 6-DoF DOBOT CR3 across unseen planar and three-dimensional trajectories show substantially faster physical-trial convergence than fixed-parameter model-based ILC. Across the four primary trajectories, after only two trial-to-trial updates, Diff-ILC achieves 78.8% and 76.4% lower mean joint-vector and Cartesian RMSE, respectively, than fixed-parameter model-based ILC.

cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01219

The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse

Samuel Harvan, Jaroslav Kopčan, Marek Šuppa, Andrej Findor

原文摘要

In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak) prompts yield a modest, task-dependent gains, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions (system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.18706

Health-SCORE: Improving Open-Ended Health LLMs Using Scalable Rubric-Based Rewards

Zhichao Yang, Sepehr Janghorbani, Dongxu Zhang, Jun Han, Qian Qian, Andrew Ressler, Gregory D. Lyng, Sanjit Singh Batra 等 9 位作者

原文摘要

Reinforcement learning is a powerful approach for improving language models, but applying it to open-ended domains such as healthcare remains challenging because high-quality responses are often multidimensional, context-dependent, and difficult to capture with a single reward signal. Rubrics offer a natural form of supervision by providing a structured representation of the criteria that define a strong response. Existing rubric-based approaches, however, often rely on instance-specific criteria, creating two important limitations: (1) such rubrics are typically unavailable for unseen examples at test time; and (2) constructing new rubrics for every instance incurs substantial reward design costs. We introduce Health-SCORE, a scalable framework that captures recurring principles of response quality in the form of reusable meta-rubrics. Rather than relying on manually constructed instance-level criteria, Health-SCORE captures generalizable principles that can be applied across examples, tasks, and healthcare datasets. These meta-rubrics support two forms of model improvement: they can serve as structured, safety-aware reward signals for reinforcement learning during post-training, and they can be incorporated directly into prompts to guide model behavior at inference time. Across several open-ended healthcare benchmarks, models trained with Health-SCORE achieve performance competitive with models trained using human-authored instance-level rewards, while substantially reducing reward-design costs and improving generalizability.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗