AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation

Shuowei Li, Yuming Zhao, Parth Bhalerao, Oana Ignat

Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Evaluations combining CLIP-based metrics, VLM-as-judge assessments, and videoquality measures show that multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency. The dataset and code are available at https://github.com/AIM-SCU/MAVEN

arXiv

MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering

Suyang Xi, Songtao Hu, Yuxiang Lai, Wangyun Dan, Yaqi Liu, Shansong Wang, Xiaofeng Yang

Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is dominated by language. This paradigm is fundamentally limited in clinical scenarios, where accurate answers often depend on subtle, localized visual evidence that cannot be reliably preserved in static embeddings. We propose \textsc{MedLVR}, a latent visual reasoning framework that introduces an explicit visual evidence state into autoregressive decoding. Instead of relying solely on text-based intermediate reasoning, \textsc{MedLVR} interleaves a short latent reasoning segment within the decoder by reusing hidden states as continuous latent steps, enabling iterative preservation and refinement of query-relevant visual evidence before answer generation. To support effective visual supervision, we adopt a two-stage training strategy: region of interest (ROI)-supervised fine-tuning aligns latent states with clinically relevant image evidence, and Visual-Latent Policy Optimization (VLPO) further optimizes latent reasoning and answer generation under outcome-level rewards. Experiments on OmniMedVQA and five external medical VQA benchmarks show that \textsc{MedLVR} consistently outperforms recent reasoning baselines and improves the average score over the Qwen2.5-VL-7B backbone from 48.3\% to 53.4\%. These results show that latent visual reasoning provides an effective mechanism for preserving diagnostically relevant visual evidence and improving the reliability of medical VQA.

arXiv

CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

Haoxuan Xu, Hanzi Wang, Guanglin Niu

Person Re-Identification (ReID) faces severe challenges from modality discrepancy and clothing variation in long-term surveillance scenario. While existing studies have made significant progress in either Visible-Infrared ReID (VI-ReID) or Clothing-Change ReID (CC-ReID), real-world surveillance system often face both challenges simultaneously. To address this overlooked yet realistic problem, we define a new task, termed Cross-Modality Clothing-Change Re-Identification (CMCC-ReID), which targets pedestrian matching across variations in both modality and clothing. To advance research in this direction, we construct a new benchmark SYSU-CMCC, where each identity is captured in both visible and infrared domains with distinct outfits, reflecting the dual heterogeneity of long-term surveillance. To tackle CMCC-ReID, we propose a Progressive Identity Alignment Network (PIA) that progressively mitigates the issues of clothing variation and modality discrepancy. Specifically, a Dual-Branch Disentangling Learning (DBDL) module separates identity-related cues from clothing-related factors to achieve clothing-agnostic representation, and a Bi-Directional Prototype Learning (BPL) module performs intra-modality and inter-modality contrast in the embedding space to bridge the modality gap while further suppressing clothing interference. Extensive experiments on the SYSU-CMCC dataset demonstrate that PIA establishes a strong baseline for this new task and significantly outperforms existing methods.

arXiv

Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection

Seoyoung Lee, Shaekh Mohammad Shithil, Durgakant Pushp, Lantao Liu, Zhangyang Wang

Inspection of confined infrastructure such as culverts often requires accessing hidden spaces whose entrances are reachable primarily from elevated viewpoints. Aerial-ground cooperation enables a UAV to deploy a compact UGV for interior exploration, but selecting a suitable deployment region from aerial observations requires metric terrain reasoning involving scale ambiguity, reconstruction uncertainty, and terrain semantics. We present a metric RGB-based geometric-semantic reconstruction and traversability analysis framework for aerial-to-ground hidden space inspection. A feed-forward multi-view RGB reconstruction backbone produces dense geometry, while temporally consistent semantic segmentation yields a 3D semantic map. To enable deployment-relevant measurements without requiring LiDAR-based dense mapping, we introduce an embodied motion prior that recovers metric scale by aligning predicted camera motion with onboard platform egomotion. From the metrically grounded reconstruction, we construct a confidence-aware geometric-semantic traversability map and evaluate candidate deployment zones under reachability constraints. Experiments on a tethered UAV-UGV platform demonstrate reliable deployment-zone identification in hidden space scenarios.

arXiv

Lipschitz-Based Robustness Certification Under Floating-Point Execution

Toby Murray

Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning, and so scales efficiently. It is increasingly used even where verifiable guarantees matter. Yet, as with most prior work on robustness certification and verification, soundness is typically proved against a semantic model assuming exact real arithmetic. Deployed networks instead execute in floating-point, creating a gap between certified properties and executed behaviour. As motivating evidence, we give counterexamples showing that real arithmetic robustness guarantees can fail under floating-point execution, even for previously verified certifiers. We then develop a formal, compositional theory relating real arithmetic Lipschitz-based sensitivity bounds to floating-point execution under standard rounding-error models for feed-forward ReLU networks. We derive sound conditions for floating-point robustness, including bounds on certificate degradation and sufficient conditions for the absence of overflow. We also give an efficient floating-point Gram iteration algorithm for Lipschitz bounds and prove that it never under-estimates the true norm. Separately, when a model is certified pre-deployment, we show how measuring its actual deviation against a high-precision execution can substantially reduce certificate degradation. We formalise the theory and its soundness, and implement an executable certifier, evaluated across dense networks spanning image, tabular, and many-class classification. To our knowledge, ours is the first method for soundly accounting for floating-point effects in Lipschitz-based robustness certification, and, done efficiently, the first floating-point-sound robustness checking procedure of any kind to certify models' entire test set -- seven those with 500,000 examples -- while retaining enough precision to be practical.

arXiv

Automated Reinforcement Learning: An Overview

Reza Refaei Afshar, Joaquin Vanschoren, Uzay Kaymak, Rui Zhang, Yaoxin Wu, Wen Song, Yingqian Zhang

Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is progressively becoming popular in other fields, such as combinatorial optimization, where researchers and system designers are not necessarily RL experts. Besides, many modeling decisions are typically made manually, such as defining state and action space, size of batches, batch update frequency, and time steps. For these reasons, automating different components of RL is of great importance, and it has attracted much attention in recent years. Automated RL provides a framework in which different components of RL, including MDP modeling, algorithm selection, and hyper-parameter optimization, are modeled and defined automatically. In this article, we present the literature on automated RL (AutoRL), including the recent large language model (LLM) based techniques. We also discuss the recent work on techniques that are not presently tailored for automated RL but hold promise for future integration into AutoRL. Furthermore, we discuss the challenges, open questions, and research directions in AutoRL.

arXiv

UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders

Matthew Walmer, Saksham Suri, Anirud Aggarwal, Abhinav Shrivastava

The space of task-agnostic feature upsampling has emerged as a promising area of research to efficiently create denser features from pre-trained visual backbones. These methods act as a shortcut to achieve dense features for a fraction of the cost by learning to map low-resolution features to high-resolution versions. While early works in this space used iterative upsampling approaches, more recent works have switched to cross-attention-based methods, which risk falling into the same efficiency scaling problems of the backbones they are upsampling. In this work, we demonstrate that iterative upsampling methods can still compete with cross-attention-based methods; moreover, they can achieve state-of-the-art performance with lower inference costs. We propose UPLiFT, an architecture for Universal Pixel-dense Lightweight Feature Transforms. We also propose an efficient Local Attender operator to overcome the limitations of prior iterative feature upsampling methods. This operator uses an alternative attentional pooling formulation defined fully locally. We show that our Local Attender allows UPLiFT to maintain stable features throughout upsampling, enabling state-of-the-art performance with lower inference costs than existing pixel-dense feature upsamplers. In addition, we apply UPLiFT to generative downstream tasks and show that it achieves competitive performance with state-of-the-art Coupled Flow Matching models for VAE feature upsampling. Altogether, UPLiFT offers a versatile and efficient approach to creating denser features.

arXiv

Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection

Jiahao Zhao

General-purpose object detection algorithms face a domain-shift bottleneck when deployed in vertical scenarios, and manually customizing a network architecture relies heavily on expert experience with high trial-and-error cost. To address these problems, we present \textbf{Cognitive-YOLO}, an adaptive object-detection model synthesis system driven by a large language model (LLM) collaborating with an autonomous agent. Cognitive-YOLO builds a fully automated \emph{Analyze--Synthesize--Compile} pipeline. First, a data-profiling module quantitatively extracts dataset features, guiding a ReAct-paradigm agent to autonomously retrieve matching network modules from a curated component library. Second, the LLM performs logical reasoning and topological assembly conditioned on the data features, producing a specification-compliant neural architecture description. Finally, a backend hybrid compiler dynamically instantiates the model, closing the loop with end-to-end training and evaluation scheduling. Cross-validation on datasets including rail-surface defects and rice diseases shows that the lightweight models synthesized by Cognitive-YOLO markedly compress the parameter count (down to 1.9M) while matching or surpassing mainstream baselines such as YOLOv11n in mAP@0.5:0.95, effectively balancing model compactness and feature-representation capability.

arXiv

Particle Image Velocimetry Refinement via Consensus ADMM for Active Fluid Control

Alan Bonomi, Francesco Banelli, Antonio Terpin

Particle Image Velocimetry (PIV) is among the central modalities for measuring flow fields across laboratory, industrial and environmental setting. Traditional PIV approaches typically depend on tuning parameters specific to the imaging setup, making the performance sensitive to variations in illumination, flow conditions, and seeding density. Similarly, state-of-the-art machine learning methods for flow quantification are fragile outside their training set. In our experiments, we observed that flow quantification would improve if different tunings (or algorithms) were applied to different regions of the same image pair. Motivated by this observation, we thus pose flow quantification as a multi-estimator fusion problem: several heterogeneous algorithms process the same image pair in parallel, and their dense flow fields are treated as complementary estimates. To fuse them, we adopt a consensus framework based on the alternating direction method of multipliers, incorporating priors such as smoothness and incompressibility. We perform several numerical experiments to demonstrate the benefits of this approach. For instance, we achieve a decrease in end-point-error of up to 20% of a dense-inverse-search estimator at an inference rate of 60Hz, and we show how performance can be increased with outlier rejection. Our method is implemented in JAX and integrated into Flow Gym, enabling reproducible comparisons with the state of the art and systematic evaluation across different base algorithms. Finally, we demonstrate successful deployment of our method in the same real-world active-fluids-control setup of Terpin and D'Andrea [1], where a reinforcement-learning agent uses our flow estimates to learn to minimize drag (down by 36%) or maximize it (up to 32%) with only two minutes of real-world interaction. Hardware and software are made available at ActiveFluidControl.com.

arXiv

MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation

Thanni Adewuyi, Anuoluwa Sotome, Samuel Okoko, Angel Ezendu, Oluwafunke Akinbuwa, Oluwaseun Odunsi, Oluwasegun Oguntuase, Ifeoma Nwabueze, Abiodun Adereni

Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of whether a system can distinguish clinically similar presentations requiring different interventions. We introduce MamaBench, the first counterfactual benchmark for maternal and paediatric AI: 434 expert-authored clinical narratives in 217 pairs across 371 pathologies, evaluated via the Bias Trap Rate (BTR), the conditional probability that a model fails the counterfactual given success on the base case. We propose Evidence-Anchored RAG (EA-RAG), a three-stage retrieval method that replaces aggregate similarity with an evidence coverage objective through clinical parameter extraction, coverage auditing, and contrastive sub-queries. Across eight configurations of four frontier LLMs, base accuracy overstates robust accuracy by 16-28 percentage points in every model. EA-RAG achieves 20.3% BTR and 65.0% robust accuracy on Claude Sonnet 4.6, a 5.5 percentage point BTR reduction without degrading base accuracy. The residual 20% BTR confirms that counterfactual robustness in clinical AI remains an open challenge. Keywords: counterfactual evaluation, clinical AI, maternal healthcare, retrieval-augmented generation, diagnostic robustness

arXiv

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Yubo Wang, Jiarong Liang, Yuxuan Zhang, Xuye Liu, Cong Wei, Yuyu Zhang, Ping Nie, Wenhu Chen

Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that masks functions selected via program dependency graph analysis and a complexity-inferability double criterion. We mid-train Qwen2.5-Coder-Instruct (7B/14B) and Qwen3-8B on a 2.6B-token decontaminated corpus drawn from 968 GitHub repositories, then apply existing agentic post-training pipelines. Mid-training improves SWE-Bench-Verified by +2.8/+3.0 at 7B/14B and by +3.2 on Qwen3-8B; SWE-Bench-Lite gains are +3.7/+4.0/+5.4 on the same models. The improvement holds across two post-training pipelines (R2E-Gym, SWE-Smith) and on a non-Qwen2.5 base (Qwen3-8B with SWE-Lego). Beyond in-domain gains, mid-training also mitigates the capability erosion that agentic post-training otherwise inflicts on non-agent coding (e.g., LiveCodeBench) and non-coding tool-use benchmarks (tau-bench, BFCL): although the mid-training corpus contains Python code only, the function-call inductive bias survives post-training and yields consistent gains.

arXiv

VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task

Xingming Long, Jie Zhang, Shiguang Shan, Xilin Chen

Most research on hallucinations in Large Vision-Language Models (LVLMs) focuses on factual description tasks that prohibit any output absent from the image. However, little attention has been paid to hallucinations in voluntary imagination tasks, such as story writing, despite this human-like cognitive ability being essential for real-world generative applications. To address this limitation, we introduce Voluntary-imagined Object Presence Evaluation (VOPE) -- a recheck-based evaluation benchmark for assessing LVLMs' grounding behavior in voluntary imagination tasks. Specifically, VOPE poses recheck-based questions to evaluate how an LVLM interprets the presence of the imagined objects in its own response. Rather than penalizing the imagined content itself, VOPE identifies hallucinations based on the correctness of the model's presence judgments for the generated objects. Built on this idea, we construct a dataset covering captioning, reasoning, and writing tasks with different levels of voluntary imagination. We apply VOPE to several mainstream LVLMs and hallucination mitigation methods, revealing two key findings: (1) most LVLMs hallucinate heavily during voluntary imagination, and their performance in presence evaluation is notably poor on imagined objects; (2) existing hallucination mitigation methods show limited effect in voluntary imagination tasks, making this an important direction for future research.

arXiv

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications

Evgeny Shilov

Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently substituting the model on 20% of tasks via an official safeguard fallback -- evidence that the deployed product, not the model, is the unit actually measured. Version 2 adds Round 2: seven further configurations on the same frozen set under a per-configuration freshness gate -- the Russian-market agents SourceCraft CLI (ds, legacy) and Koda CLI (koda-pro), Antigravity with Gemini 3.1 Pro and 3.5 Flash, and Codex CLI with GPT-5.6 Sol and Luna. SourceCraft's flagship resolves 68.1% (N=23), above GPT-5.5 and both Gemini rows. A tool-call contamination re-audit of all 437 Round-2 trajectories finds the Russian and Gemini columns clean (0/293 cells) while flagging systematic oracle-hunting in the GPT-5.6 family (8/69 and 13/75 cells), including one case of mining a prior round's artifacts from the run machine's disk; honest scores are published alongside raw ones. We release statements, metadata, trajectories, and diffs; oracles are withheld with a SHA-256 manifest.

arXiv

Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents

Yusuf Khan, Carlo Lipizzi

Language agents run a loop - observe, reason, act - but the memory they reason over sits outside it: a store queried at most once per turn. We study the regime where memory moves inside the loop, read and written on every step. The obstacle has always been latency: networked stores answer in tens to hundreds of milliseconds, and in-loop retrieval can inflate end-to-end latency by up to 83x when retrieval is expensive. Prior work manages that cost rather than questioning it: serving-layer scheduling hides it, "memory-first" designs ration retrieval to once per turn. We argue latency is a property of where the store lives, not the in-loop pattern: an in-process store answers in ~100us, three orders of magnitude below the network regime, and at that speed the per-step tax collapses. By the extended-mind thesis's parity principle, a store fast enough to be constantly and directly available becomes extended working memory, not a tool the agent merely consults. The premise is causal: holding a fixed per-turn memory-latency budget and varying only the store's answer speed, redundant actions rise monotonically with latency - 0.0 of 12 at in-process speed, 7.2 of 12 at a 110ms cloud round trip (gpt-5-nano, gpt-5-mini; exact permutation p=0.0079). We demonstrate the regime end-to-end: across four GPT-5-class models under a bounded window, recall improves from 0/5 to 3.6-4.8/5 with in-loop memory, store ops at p50 80-165us - though an instructed restate-every-reply baseline also solves it perfectly, at a token cost that grows with the working set. The store never lost a fact in any run (244 of 244 writes kept); every miss traces to the agent's read policy, not the store. Our measurements also relocate the bottleneck: the dominant per-step cost is embedding (~200-400ms over the network); pairing the in-process store with a small local embedder returns the complete operation to a measured ~40us.

arXiv

Improving Answer Extraction in Context-based Question Answering Systems Using LLMs

Hafez Abdelghaffar, Ahmed Alansary, Ali Hamdi

Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs). However, they still face challenges in accurately extracting and generating precise answers from given contexts, particularly when dealing with complex or ambiguous queries. Existing approaches often struggle with contextual understanding, answer consistency, and generalization across diverse domains. In this work, we propose a question answering system based on large language models, where the input consists of a textual context and a corresponding question, and the output is a concise and accurate answer. The motivation behind this research lies in addressing the limitations of current QA systems, particularly their tendency to produce irrelevant or imprecise responses despite having access to the correct context. Our methodology involves fine-tuning a pre-trained LLM on a benchmark QA dataset to improve its contextual comprehension and answer extraction capabilities. Specifically, we utilize the Stanford Question Answering Dataset (SQuAD1.1), which provides high-quality context-question-answer triplets for supervised training and evaluation. Experimental results show that the fine-tuned Roberta-base model achieves the highest performance, attaining a ROUGE-L score of 86.84%, a BLEU score of 28.24%, and a BERTScore of 95.38%. These results indicate strong accuracy and answer relevance, demonstrating the effectiveness of the proposed approach for context-based question answering tasks. Furthermore, the findings confirm that targeted fine-tuning substantially improves the reliability and precision of QA systems.

arXiv

Taxonomy-Targeted Error Generation for Quantitative Reasoning

Xinming Yang, Jun Li

Personalized tutoring, teacher preparation, and education research can benefit from worked errors annotated by the mechanisms that produced them. Authentic student errors with such cognitive labels are costly to collect and share, motivating the study of whether LLMs can generate taxonomy-targeted synthetic errors as complementary candidate material. We present a task-specific framework that generates errors targeted to a five-class Bloom-informed student-error taxonomy. A Generation Agent (GA) drafts a candidate erroneous solution conditioned on a target class, and an Examination Agent (EA) judges whether the draft is incorrect and class-consistent. The framework yields a reusable recipe for building class-stratified synthetic error datasets where authentic student corpora are unavailable. As a secondary diagnostic, targeted error generation is substantially harder than free-form incorrect-answer generation, and answer-grounding contributes more than expanded examples or external textbook content.

arXiv

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict

Yihang Chen, Pin Qian, Su Wang, Sipeng Zhang, Huan Xu, Shuhuai Lin, Xinpeng Wei

Retrieval-Augmented Generation (RAG) is usually evaluated by whether the final answer is correct. Under knowledge conflict, this hides a key question: did the model follow retrieved evidence, rely on its parametric prior, or produce a post-hoc rationale? We study this as context compliance, the regime in which retrieved context controls the answer even when it conflicts with the model's prior knowledge. We introduce Context-Driven Decomposition (CDD), an inference-time diagnostic intervention that elicits contextual and prior answers, isolates the conflicting premise, and records a resolution trace that can be perturbed. Across Epi-Scale stress tests, TruthfulQA misconception injection, and cross-model reruns, CDD makes three behaviors visible. First, misleading retrieval can severely degrade accuracy: under a worst-case TruthfulQA misconception-injection probe, Standard RAG reaches only 15.0%. Second, better answers need not share the same mechanism: CDD improves adversarial accuracy on Gemini-2.5-Flash and shows directional gains across Claude variants, yet trace-perturbation sensitivity is high only on Gemini. Third, explicit decomposition improves controlled-conflict robustness over a conflict-aware instruction baseline on localized factual conflicts, with the clearest margins on Entity Swap (88.0% vs 79.3%) and Logical Contradiction (83.2% vs 75.4%). We frame RAG conflict handling as an observability problem.

arXiv

History-Aware Transformation of ReID Features for Multiple Object Tracking

Ruopeng Gao, Yuyao Wang, Chunxu Liu, Limin Wang

In Multiple Object Tracking (MOT), Re-identification (ReID) features are widely employed as a powerful cue for object association. However, they are often wielded as a one-size-fits-all hammer, applied uniformly across all videos through simple similarity metrics. We argue that this overlooks a fundamental truth: MOT is not a general retrieval problem, but a context-specific task of discriminating targets within a single video. To this end, we advocate for the adjustment of visual features based on the context specific to each video sequence for better adaptation. In this paper, we propose a history-aware feature transformation method that dynamically crafts a more discriminative subspace tailored to each video's unique sample distribution. Specifically, we treat the historical features of established trajectories as context and employ a tailored Fisher Linear Discriminant (FLD) to project the raw ReID features into a sequence-specific representation space. Extensive experiments demonstrate that our training-free method dramatically enhances the discriminative power of features from diverse ReID backbones, resulting in marked and consistent gains in tracking accuracy. Our findings provide compelling evidence that MOT inherently favors context-specific representation over the direct application of generic ReID features. We hope our work inspires the community to move beyond the naive application of ReID features and towards a deeper exploration of their purposeful customization for MOT. Our code will be released. The code is released at https://github.com/MCG-NJU/HATReID-MOT.

arXiv

The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices

Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann, Matthias Aßenmacher

Why does machine-generated text remain detectable? We trace the answer to the decoding stage: standard strategies such as top-$k$ and nucleus sampling restrict generation to high-probability tokens, while human writers routinely choose words that are contextually apt yet rank low under a model's next-token distribution. Truncation therefore renders a measurable share of human word choices unreachable; we call this set the truncation blind spot. Across five open models and three domains, 8--18\% of human-selected tokens fall outside common truncation boundaries, with content words excluded at 2.9 times the rate of function words. As a consequence, simple classifiers using two features separate 1.8 million machine generations from human text at mean AUC-ROC near 0.97, and detectability tracks truncation intensity rather than model scale, architecture, or alignment. Probability-floor samplers substantially narrow the blind spot, and generation experiments confirm the exclusion--detectability link out of sample. Code, data, and the measurement harness are released at https://github.com/EstebanGarces/human_vs_machine.

arXiv

Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors

Qiming Bao, Xiaoxuan Fu, Michael Witbrock

Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential rule deletion, contradictory-rule injection, logic-preserving rewrites, and multi-law stacking -- and use it to expose Logic Inertia: the tendency of generative LLMs (Qwen2/3, TinyLlama, GPT-4o, Gemma-3-4B-IT) and the encoder-only BERT baseline to persist along learned deductive trajectories under inconsistent premises. The collapse is sharp: untreated baselines fall from accuracy 1.00 on the base task to 0.00 on contradiction injection (instance-level exact match), and GPT-4o resolves only 56.0% of contradiction cases. We propose Conflict-Aware Fusion, a four-stage training pipeline that enforces verification-before-deduction as a learned structural prior: (i) SFT establishes the verification preamble; (ii) DPO sharpens the halt-on-contradiction decision boundary; (iii) Logical Invariance REgularisation (LIRE) penalises divergence between logically equivalent rule formulations via symmetric KL; (iv) Reinforcement Learning from Verification Feedback (RLVF) uses a symbolic forward-chaining engine as a deterministic oracle reward, jointly optimising invariance and sensitivity. The pipeline saturates all four primary stress tests for both 1.5B and 8B backbones. We further validate a Phase 2 extension that replaces the propositional oracle with a Lean 4 kernel, attaining 99.0% kernel agreement on the 105 classically-derivable (T) questions within a stratified 187-question Lean-translated sample (overall 71.7% across both polarities), providing a sound upgrade path to formally verified RL training. Code and benchmark: https://github.com/14H034160212/lemo

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.