AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWorking with AI: A Design Framework for Human-AI Collaboration
arXiv:2609.31793v1 Announce Type: new Abstract: Artificial Intelligence (AI), particularly GenAI, is becoming an increasingly important part of modern work. In industrial settings, AI can support decision-making, automat…
- arXiv cs.AIresearchLLM Judge Validation Under Sparse Overlap: From Inference to Design
arXiv:2609.31857v2 Announce Type: replace Abstract: Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this ov…
- arXiv cs.AIresearchMetro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals
arXiv:2609.31868v3 Announce Type: replace Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effective over short pl…
- arXiv cs.AIresearchIndustryLLM: Failure-Driven LLM Training for Industrial Procurement
arXiv:2609.31871v1 Announce Type: new Abstract: Industrial procurement requires language models to bridge informal buyer jargon, sparse marketplace attributes, and authoritative engineering standards under strict safety…
- arXiv cs.AIresearchImproving Medical Calculation of LLMs with Embedded Coding
arXiv:2609.31908v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on medical examinations and question-answering benchmarks, but remain unreliable on medical calculation tasks that require exact n…
- arXiv cs.AIresearchWhat Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation
arXiv:2609.32002v2 Announce Type: replace Abstract: The rank $r$ in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that, under hard per-f…
- arXiv cs.AIresearchA Benchmark for LLM's Understanding of Middle School and High School Science Topics
arXiv:2609.32020v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into educational settings, yet educators lack robust, standards-aligned tools to evaluate their effectiveness in K-…
- arXiv cs.AIresearchReasoning Concentrates Errors, and Self-Consistency Never Notices
arXiv:2609.32035v1 Announce Type: new Abstract: Self-consistency assumes that independent samples disagree when a model is unsure, so agreement is evidence of correctness. Holding weights fixed and toggling only a reason…
- arXiv cs.AIresearchResidual Streams Read, Recurrent States Remember: The Global Workspace in Mamba Models
arXiv:2609.32102v1 Announce Type: new Abstract: Can the global-workspace account of transformer representations extend to state-space language models? We fit Jacobian lenses to the residual streams and recurrent states o…
- arXiv cs.AIresearchEscaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking
arXiv:2609.32116v1 Announce Type: new Abstract: Best-of-$N$ jailbreaking (BoN) bypasses safeguards of aligned models by drawing $N$ independent augmentations of an unsafe prompt and sampling $M$ completions of each. Prev…
- arXiv cs.AIresearchREAD-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis
arXiv:2609.32123v2 Announce Type: replace Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through downstream predicti…
- arXiv cs.AIresearchNoisy Test-Time Reinforcement Learning for Code LLMs
arXiv:2609.32172v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance across various code-related tasks. However, unlike carefully curated datasets that are typically high-…
- arXiv cs.AIresearchInstruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation
arXiv:2609.32201v2 Announce Type: replace Abstract: On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the tea…
- arXiv cs.AIresearchFracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
arXiv:2609.32209v1 Announce Type: new Abstract: Time series foundation models must preserve multi-domain breadth, probabilistic output, and multiple temporal scales, but parameter count grows when each scale receives a s…
- arXiv cs.AIresearchA bilingual AI audiologist built through rubric-guided closed-loop engineering outperforms human audiologists in a blinded evaluation of simulated cases
arXiv:2609.32220v2 Announce Type: replace Abstract: Audiology consultation requires structured history-taking, audiometric interpretation and patient-centred communication, yet real-world case material is scarce. We pres…
- arXiv cs.AIresearchRAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
arXiv:2609.32224v1 Announce Type: new Abstract: We explore whether Omni-Language Models (OLMs) can be directly applied to zero-shot Semantic Audio-Visual Navigation (SAVN). Recent work demonstrates that even state-of-the…
- arXiv cs.AIresearchCertifying Interventional Agreement Among Observationally Equivalent Causal Models
arXiv:2609.32247v1 Announce Type: new Abstract: Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occur in observational dat…
- arXiv cs.AIresearchWhy Directly Learning Periodic Trajectories Can Fail
arXiv:2609.32254v1 Announce Type: new Abstract: Operator learning of periodic solutions requires deciding how simulation data should be recorded and represented. A natural choice is to integrate long enough for transient…
- arXiv cs.AIresearchTrain4Merge: RL or SFT---Which Yields Better Teachers for OPD-Based Model Merging?
arXiv:2609.32303v3 Announce Type: replace Abstract: Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research…
- arXiv cs.AIresearchPhiFold: Towards Dynamic Protein Design with Physics-Structured Covariance Modeling
arXiv:2609.32309v1 Announce Type: new Abstract: Protein design is moving beyond structural correctness toward function-aware design, yet existing generative models typically treat dynamics as a downstream property estima…
- arXiv cs.AIresearchDelayed Supervision for Test-Time Language Models
arXiv:2609.32312v1 Announce Type: new Abstract: Test-time language models adapt a compact memory while processing the input sequence. This perspective encompasses nonlinear fast-weight learning in LaCT, associative delta…
- arXiv cs.AIresearchRLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning
arXiv:2609.32326v1 Announce Type: new Abstract: Multimodal reasoning requires models to preserve visual evidence through long decision chains while selecting appropriate procedures across diverse scenarios and rules. Whe…
- arXiv cs.AIresearchHyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning
arXiv:2609.32327v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities, with retrieval-augmented generation (RAG) supporting complex multi-hop reasoning by retrieving evidence distrib…
- arXiv cs.AIresearchALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs
arXiv:2609.32344v1 Announce Type: new Abstract: For large language models (LLMs), parametric adaptation is costly when retrieval already suffices. We introduce ALLOT, a hybrid-memory routing framework that separates lear…
- arXiv cs.AIresearchMemory as a cache: Exact context reuse and deletion by construction
arXiv:2609.32395v1 Announce Type: new Abstract: The KV cache of a transformer entangles every token's representation with its entire prefix: a passage encoded once cannot be reused under a different prefix or removed wit…
- arXiv cs.AIresearchFunction Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism
arXiv:2609.32398v1 Announce Type: new Abstract: The scaling of LLMs increasingly relies on MoE architectures to decouple active computation from total parameter count. However, the efficacy of MoE is often constrained by…
- arXiv cs.AIresearchOpening LLM Judges: Recovering Preference Signals Beyond the Final Verdict
arXiv:2609.32407v1 Announce Type: new Abstract: LLM judges are widely used to evaluate model outputs, but their verdicts can be unreliable: a judge may favor the worse answer for its position, length, or other surface fe…
- arXiv cs.AIresearchCarnator: Fast Text-to-Video Generation with Generation-Native Compatibility-Guided Cross-Request Reuse
arXiv:2609.32420v1 Announce Type: new Abstract: Video diffusion transformers produce high-quality videos, yet iterative denoising incurs substantial inference latency, limiting interactive and large-scale serving. Most e…
- arXiv cs.AIresearchMergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging
arXiv:2609.32422v1 Announce Type: new Abstract: Model merging consolidates task-specialized experts into a single deployable model. However, we show that such capability consolidation incurs a merging tax of increased ha…
- arXiv cs.AIresearchPrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
arXiv:2609.32429v2 Announce Type: replace Abstract: Smaller activation outliers do not necessarily imply better low-bit quantization: their alignment with the quantizer matters. We introduce PrismQuant, a quantizer-aware…
- arXiv cs.AIresearchFrom Latents to Wires: Surgical Post-Editing on Large Language Models
arXiv:2609.32434v1 Announce Type: new Abstract: Given a large language model (LLM), can whoever holds the weights name a semantic target (e.g., the model's identity), locate the model components that produce it, and edit…
- arXiv cs.AIresearchControllable GNN Explanations via Multi-Metric Preference Selection
arXiv:2609.32436v2 Announce Type: replace Abstract: Mechanisms for generating GNN explanations are crucial for building trust and mitigating biases in Graph Neural Networks (GNNs), especially in high-stakes scenarios. Mo…
- arXiv cs.AIresearchForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation
arXiv:2609.32448v1 Announce Type: new Abstract: Autoregressive Next-Token Prediction (NTP) has enabled strong reasoning capabilities in language models, while Diffusion Language Models (DLMs) offer flexible token orders…
- arXiv cs.AIresearchPULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders
arXiv:2609.32469v1 Announce Type: new Abstract: In-context learning is highly sensitive to demonstration choice, yet most methods select demonstrations using external query-demonstration similarity. Such criteria can mis…
- arXiv cs.AIresearchVPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography
arXiv:2609.32473v1 Announce Type: new Abstract: Optical proximity correction (OPC) recipes grow as engineers add local rules to repair newly discovered lithography hotspots. Each correction can interact with existing rul…
- arXiv cs.AIresearchFrom Outcomes to Strategies: Learning Strategy Utility for Mathematical Reasoning
arXiv:2609.32482v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has substantially improved mathematical reasoning. However, terminal correctness alone provides limited insight into the qual…
- arXiv cs.AIresearchSeparating Diagnosis from Disease Representation: Dual-View EEG Learning with Neural-Dynamics-Guided Deformation
arXiv:2609.32483v1 Announce Type: new Abstract: Electroencephalography (EEG)-based closed-loop neuromodulation calls for a subject-specific structured state, as opposed to a single disease probability, specifying which b…
- arXiv cs.AIresearchTowards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling
arXiv:2609.32484v1 Announce Type: new Abstract: Data selection for language model pretraining faces a fundamental tension between quality and diversity. While quality filtering is empirically effective, it often induces…
- arXiv cs.AIresearchWhen Helpful Text Hurts: Option-Redirecting Bias in Vision-Language Models
arXiv:2609.32489v1 Announce Type: new Abstract: In tri-modal visual question answering (VQA), auxiliary text is commonly used to complement visual and textual inputs, yet its reliability is often uncontrolled. While prio…
- arXiv cs.AIresearchBeyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
arXiv:2609.32492v1 Announce Type: new Abstract: Large language models can solve increasingly diverse reasoning tasks, yet their performance remains highly sensitive to task prompts, intermediate instructions, and the way…
- arXiv cs.AIresearchTreeRef-BFN: Equivariance-Free De Novo Molecule Generation based on 2D Topology and Internal 3D Geometry
arXiv:2609.32502v1 Announce Type: new Abstract: De novo 3D molecular generation jointly models molecular size, topology, and geometry. Most methods pre-sample molecular size and generate Cartesian coordinates, limiting v…
- arXiv cs.AIresearchLocalProp: Neuro-Localized Memory-Efficient Backpropagation
arXiv:2609.32517v1 Announce Type: new Abstract: The current deep learning training paradigm employs end-to-end backpropagation, regardless of the training stage, i.e. pre-training or fine-tuning. However, backpropagating…
- arXiv cs.AIresearchSTR: Supervised Transcoder Replacement for Reducing Steering Side Effects
arXiv:2609.32519v1 Announce Type: new Abstract: Model steering can strengthen a target behavior while degrading other useful behaviors. We introduce Supervised Transcoder Replacement (STR) to reduce these side effects fo…
- arXiv cs.AIresearchAmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses
arXiv:2609.32527v1 Announce Type: new Abstract: Predicting cellular responses to genetic perturbations helps prioritize experiments in single-cell genomics, where exhaustive measurement is infeasible. While computational…
- arXiv cs.AIresearchLLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses
arXiv:2609.32533v1 Announce Type: new Abstract: Inserting advertisements (ads) into consumer-facing LLM output is emerging as a new business model, but there is little shared evidence on how such ad insertion should be e…
- arXiv cs.AIresearchInterpretable Physics Informed WiFi Indoor Localization: Learning an Effective Access Point Geometry and Using It to Prune
arXiv:2609.32539v1 Announce Type: new Abstract: Deep learning models can achieve high accuracy for indoor localization, but their black-box nature limits interpretability and the reuse of learned information. We propose…
- arXiv cs.AIresearchAre Vision-Language-Action Models Robust to One-Step Observation Perturbations?
arXiv:2609.32550v1 Announce Type: new Abstract: Understanding the safety risks of vision-language-action (VLA) models is essential for their deployment in the physical world. Existing safety research has mainly considere…
- arXiv cs.AIresearchArtificial intelligences and human scientists exhibit complementary strengths in theory building
arXiv:2609.32562v1 Announce Type: new Abstract: We investigate the effectiveness of artificial intelligences (AI)-specifically large language models (LLMs)-relative to human scientists at high-level cognitive tasks in so…
- arXiv cs.AIresearchProTTT: Learning to Learn Semantic User Memory with Test-Time Training
arXiv:2609.32564v1 Announce Type: new Abstract: Personalization requires language models to capture user-specific knowledge from a growing user history. Existing context-based approaches incur increasing inference costs…
- arXiv cs.AIresearchCan Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study
arXiv:2609.32638v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate synthetic survey respondents and digital twins of real people, but whether their output preserves real human…