AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchA Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs
arXiv:2610.18200v1 Announce Type: cross Abstract: Parallel generation is widely regarded as an inherent advantage of diffusion large language models. Yet our fixed-quota evaluation of four representative models reveals s…
- arXiv cs.AIresearchHow Reliable Are Large Language Models for Soil Organic Carbon Assessment? An Australian Benchmark
arXiv:2610.18201v1 Announce Type: cross Abstract: Soil organic carbon (SOC) is an indicator of agricultural soil condition and carbon storage, but numerical outputs from large language models (LLMs) require validation be…
- arXiv cs.AIresearchReset Early, Reset Often, Eliminate Models
arXiv:2610.18204v1 Announce Type: cross Abstract: Connection-tableau provers typically construct closed tableaux by backtracking search. This gives lightweight proof procedures, but their low-memory search state leaves l…
- arXiv cs.AIresearchA Controlled Evaluation of Curvature Inspired Scalar Feature Scaling for Domain Generalization
arXiv:2610.18227v1 Announce Type: cross Abstract: Domain-specific curvature is an appealing idea for domain generalization (DG), but curvature learning can denote substantially different computations. This paper evaluate…
- arXiv cs.AIresearchHeading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
arXiv:2610.18238v1 Announce Type: cross Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. H…
- arXiv cs.AIresearchLiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
arXiv:2610.18243v1 Announce Type: cross Abstract: Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed tomography (NCCT) is increasingly used for opportunistic screening becau…
- arXiv cs.AIresearchFALLNEST: Dual-Domain Dataset Condensation of Imbalanced IMU Data for Wearable Fall Detection
arXiv:2610.18260v1 Announce Type: cross Abstract: Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Existing methods eith…
- arXiv cs.AIresearchWhich Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller
arXiv:2610.18294v1 Announce Type: cross Abstract: Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training. We ask whether…
- arXiv cs.AIresearchAffectWorld: Benchmarking Emotion-Driven Future World Prediction
arXiv:2610.18305v1 Announce Type: cross Abstract: The world encompasses both physical environments and human actors. Predicting its evolution requires understanding both physical laws and how emotions shape human actions…
- arXiv cs.AIresearchSimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
arXiv:2610.18308v1 Announce Type: cross Abstract: Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic simulation possible but…
- arXiv cs.AIresearchShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
arXiv:2610.18325v1 Announce Type: cross Abstract: Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model i…
- arXiv cs.AIresearchLightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English
arXiv:2610.18343v1 Announce Type: cross Abstract: Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as…
- arXiv cs.AIresearchLet the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation
arXiv:2610.18352v1 Announce Type: cross Abstract: A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progre…
- arXiv cs.AIresearchPRISM: Calibrating Black-Box Judges with Counterfactual Probes
arXiv:2610.18389v1 Announce Type: cross Abstract: Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments. We…
- arXiv cs.AIresearchGraph-free Retrieval with Graph-Modified Embeddings
arXiv:2610.18410v1 Announce Type: cross Abstract: Dense vector retrieval can miss evidence connected through intermediate entities, while direct graph retrieval requires access to the graph at query time. We compare five…
- arXiv cs.AIresearchNot All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs
arXiv:2610.18412v1 Announce Type: cross Abstract: Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuous prompts. These…
- arXiv cs.AIresearchDo Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison
arXiv:2610.18415v1 Announce Type: cross Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment steps such as RLHF do n…
- arXiv cs.AIresearchAgaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages
arXiv:2610.18420v2 Announce Type: replace-cross Abstract: We present Agaram 2.5B, a Tamil-first language model trained from scratch that converses in Tamil script, romanized Tanglish and English, and calls tools. Our fir…
- arXiv cs.AIresearchFedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation
arXiv:2610.18430v1 Announce Type: cross Abstract: Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits.…
- arXiv cs.AIresearchHow Well Do LLMs Perform in Peer Review? Evidence from Finance and Accounting
arXiv:2610.18435v1 Announce Type: cross Abstract: Referees increasingly use large language models (LLMs), while finance and accounting journals disagree about whether to allow it. We ask which part of a referee's job the…
- arXiv cs.AIresearchSTAMP as a topology-aware molecular language for fragment-level learning and editing
arXiv:2610.18438v1 Announce Type: cross Abstract: Molecular fragments provide chemically meaningful units, but existing molecular languages rarely make their locations and connections explicit for editing. Here we introd…
- arXiv cs.AIresearchLearning Perturbation-Specific Representations through Conditional Energy Prior for Cellular Response Prediction
arXiv:2610.18456v1 Announce Type: cross Abstract: AI-based cellular perturbation prediction is essential to accelerate drug discovery and therapeutic identification. However, perturbation-specific signals are generally o…
- arXiv cs.AIresearchReadout Scaling Shapes Sparse Feature Recovery
arXiv:2610.18462v2 Announce Type: replace-cross Abstract: Readout scaling changes what a sparse autoencoder (SAE) learns, but the benefit of removing it depends on the data. We use readout-canonicalized decision-space (R…
- arXiv cs.AIresearchMemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation
arXiv:2610.18478v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-horizon trajectorie…
- arXiv cs.AIresearchTask-evoked eye movements as candidate digital biomarkers of depression severity in adolescents and young adults
arXiv:2610.18494v1 Announce Type: cross Abstract: Objective digital measures of depression severity could complement conventional symptom assessments and facilitate more timely clinical evaluation. Here, we investigated…
- arXiv cs.AIresearchAligning Faithfulness for Theory-Scale Autoformalization
arXiv:2610.18498v1 Announce Type: cross Abstract: Autoformalization (AF) requires more than compilation: formal statements must preserve the meaning of their informal sources, a property known as faithfulness. An emergin…
- arXiv cs.AIresearchEgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions
arXiv:2610.18499v1 Announce Type: cross Abstract: Egocentric video understanding spans diverse capabilities, modalities, and evaluation formats, yet these are often studied in isolation despite their tight coupling in re…
- arXiv cs.AIresearchThe Geometry of Language Model Logits: Generic Structure and Learned Departures
arXiv:2610.18520v1 Announce Type: cross Abstract: Autoregressive language models produce, at every prediction step, a vocabulary-sized logit vector whose structure determines the conditional next-token distribution. We e…
- arXiv cs.AIresearchAPTree: Extended Behavior Trees for Adaptive and Scalable Automated Robotic Task Planning in Construction
arXiv:2610.18523v1 Announce Type: cross Abstract: Task planning for robots in off-site construction prefabrication is primarily manual, leading to planning inefficiencies and reluctance to adopt robotic solutions. Existi…
- arXiv cs.AIresearchThe Many Morals of AI: The cautionary bias of North American news narratives in global perspective
arXiv:2610.18573v1 Announce Type: cross Abstract: The stories told about artificial intelligence (AI) play a central role in shaping public understanding, policy debates, and expectations about technological change. News…
- arXiv cs.AIresearchWhen More Objectives Make Identification Easier: The Role of Preferences and Feedback
arXiv:2610.18577v1 Announce Type: cross Abstract: Best-arm identification (BAI) aims to identify the optimal arm using as few samples as possible. While most existing work focuses on a single objective, many real-world a…
- arXiv cs.AIresearchGeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition
arXiv:2610.18587v1 Announce Type: cross Abstract: Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as speech and text. Psychological studies…
- arXiv cs.AIresearchACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
arXiv:2610.18596v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more: learning new tasks…
- arXiv cs.AIresearchPhysicsSliders: Learning Physical Controls for Audio Foley Generation
arXiv:2610.18597v1 Announce Type: cross Abstract: Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictably to these controls,…
- arXiv cs.AIresearchRethinking Projector Training in Multimodal LLMs
arXiv:2610.18598v1 Announce Type: cross Abstract: Multimodal LLMs are typically trained by first aligning a vision encoder with a language model via projector training on large image-caption datasets, followed by joint t…
- arXiv cs.AIresearchLLM2R: From Large Language Models to 3D Reassemblers
arXiv:2610.18604v1 Announce Type: cross Abstract: 3D part assembly aims to reconstruct a complete shape from a set of unassembled parts by predicting a rigid SE(3) transformation for each part. Because the placement of a…
- arXiv cs.AIresearchDPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
arXiv:2610.18609v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal preference data remai…
- arXiv cs.AIresearchNudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
arXiv:2610.18612v1 Announce Type: cross Abstract: System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structured judgments that directly drive program execution.…
- arXiv cs.AIresearchDoes self-distillation improve reasoning?
arXiv:2610.18613v1 Announce Type: cross Abstract: Self-distillation is an emerging approach that trains a model to imitate its own predictions when conditioned on privileged information, such as correct answers or enviro…
- arXiv cs.AIresearchFalsification-proof non-market allocation mechanisms
arXiv:2610.18625v2 Announce Type: replace-cross Abstract: Relying on manipulable characteristics to target the allocation of resources is fraught with difficulties. Naively optimal rules lead to falsification and allocat…
- arXiv cs.AIresearchGeometric Calibration of Supervised Fine-Tuning
arXiv:2610.18634v1 Announce Type: cross Abstract: Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions. Within this view,…
- arXiv cs.AIresearchDTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models
arXiv:2610.18635v1 Announce Type: cross Abstract: The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture…
- arXiv cs.AIresearchST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction
arXiv:2610.18645v1 Announce Type: cross Abstract: Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences. PredRNN and its successor PredRNN-…
- arXiv cs.AIresearchTiny Recursive Message Passing
arXiv:2610.18649v1 Announce Type: cross Abstract: Message passing neural networks have shown remarkable performance in algorithmic and constraint reasoning, due to their ability to encode the structure of the task direct…
- arXiv cs.AIresearchAMemOps: Evaluating Memory Updates in Long Audio Streams
arXiv:2610.18652v1 Announce Type: cross Abstract: Audio memory must recognise recurring sources across acoustic changes while keeping their attributes up to date. Overall accuracy does not reveal how these demands intera…
- arXiv cs.AIresearchKwai Summary Attention V2 Technical Report
arXiv:2610.18654v2 Announce Type: replace-cross Abstract: Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave t…
- arXiv cs.AIresearchKnown-Voice Cloning and the Limits of Personality Transfer for Character Design
arXiv:2610.18669v1 Announce Type: cross Abstract: Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrary virtual characters…
- arXiv cs.AIresearchSMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation
arXiv:2610.18672v1 Announce Type: cross Abstract: Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts. This…
- arXiv cs.AIresearchFrom Relation-Specific Heads to Shared Interventions: Contextual Entrainment in Language Models
arXiv:2610.18674v1 Announce Type: cross Abstract: Large language models rely on prompt context to perform in-context learning, follow formats, and adapt to local evidence. This ability, however, also raises a robustness…
- arXiv cs.AIresearchModel-Based Online Decision Making via Generative Trajectory Planning
arXiv:2610.18677v1 Announce Type: cross Abstract: Online decision-making faces a tension between efficient inference and long-horizon reasoning. Value-based methods rely on short-horizon bootstrapping that limits the pro…