AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchBig-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments
arXiv:2610.15634v1 Announce Type: new Abstract: Sycophancy in large language models risks amplifying unsupported claims or beliefs across the knowledge ecosystem as these systems increasingly contribute to research synth…
- arXiv cs.AIresearchKnowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition
arXiv:2610.15677v1 Announce Type: new Abstract: Continual learning aims to adapt pretrained large language models (LLMs) to evolving data while preserving their pretrained capabilities. A central challenge is catastrophi…
- arXiv cs.AIresearchRadioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision
arXiv:2610.15685v1 Announce Type: new Abstract: Conventional distillation transfers capability through teacher-generated demonstrations. LLM-as-a-Judge knowledge distillation offers a distinct and increasingly practical…
- arXiv cs.AIresearchFARL: A Fully Automated Pipeline of RL Interface and Solver Design
arXiv:2610.15691v1 Announce Type: new Abstract: Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies he…
- arXiv cs.AIresearchHistory Replays Itself: Unleashing Long-Context Capability in Linear Attention
arXiv:2610.15715v1 Announce Type: new Abstract: Linear attention promises the efficiency needed for long-context language modelling, yet its fixed-size recurrent state must simultaneously support ongoing computation and…
- arXiv cs.AIresearchVisible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops
arXiv:2610.15738v1 Announce Type: new Abstract: LLM optimization loops often show the proposer the candidates it has already tried and rejected, but leave it to the proposer to avoid them. We ask whether avoidance measur…
- arXiv cs.AIresearchPassing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation
arXiv:2610.15797v2 Announce Type: replace Abstract: Planning and revision are intended to bring generated code closer to the task specification. Yet a mistaken interpretation can persist across the plan, implementation,…
- arXiv cs.AIresearchAttention Sinks in VLMs Are Borrowed, Not Seen
arXiv:2610.15855v2 Announce Type: replace Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large share of attent…
- arXiv cs.AIresearchEngram Injection: A Study of Temporal Validity in Parametric Language-Model Memory
arXiv:2610.15882v2 Announce Type: replace Abstract: A stored fact may stop being valid when a user changes a preference or an event replaces an earlier one. We study whether a language model can learn these changes in it…
- arXiv cs.AIresearchComparative Study of Canvas- and Coordinate-Based Geometry-Conditioned Neural Networks for Real-Time Prediction of Indoor Environments with Varying Room Dimensions
arXiv:2610.15885v1 Announce Type: new Abstract: Computational fluid dynamics (CFD) is computationally expensive for iterative building design. Deep learning surrogates offer faster predictions, but generalization across…
- arXiv cs.AIresearchLURE: a Phase-Labelled Synthetic Corpus of Online-Grooming Exchanges
arXiv:2610.15908v1 Announce Type: new Abstract: Phase-annotated conversational data is essential for studying the progression of online grooming of minors and for developing early warning tools. However, the only publicl…
- arXiv cs.AIresearchMulti-Horizon Explainable Queue Forecasting and Resource-Aware Decision Support for Intelligent Border Control Using LightGBM
arXiv:2610.15930v1 Announce Type: new Abstract: Border crossing points are stochastic service systems in which traffic demand, traveler categories, registration status, inspection requirements, staffing, and lane availab…
- arXiv cs.AIresearchThe Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much
arXiv:2610.15938v1 Announce Type: new Abstract: Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown remains unresolved. We…
- arXiv cs.AIresearchADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation
arXiv:2610.15956v1 Announce Type: new Abstract: Vision-language-action models for embodied navigation typically rely on RGB observations, limiting their applicability in lights-out industrial environments where visible i…
- arXiv cs.AIresearchHandoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing
arXiv:2610.15993v1 Announce Type: new Abstract: We study how initial model selection, later handoff, and training targets affect success and cost in LLM tasks that span multiple turns. We compare several router architect…
- arXiv cs.AIresearchLarge language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework
arXiv:2610.15994v1 Announce Type: new Abstract: Representing individual-level behavioral heterogeneity is challenging in epidemiological modeling, particularly when empirical behavioral data are sparse. We assess the pot…
- arXiv cs.AIresearchCross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings
arXiv:2610.16050v1 Announce Type: new Abstract: Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded evaluation for job a…
- arXiv cs.AIresearchBeyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV
arXiv:2610.16074v1 Announce Type: new Abstract: Co-circulating influenza, COVID-19, and respiratory syncytial virus (RSV) create a shared hospital-admission burden, because beds, staff, testing capacity, and respiratory…
- arXiv cs.AIresearchThe Sharp Directions Are Against You: Curvature Analysis of Activation Steering
arXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. T…
- arXiv cs.AIresearchGUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines
arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consensus formation limit…
- arXiv cs.AIresearchConstructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting
arXiv:2610.16110v1 Announce Type: new Abstract: Ultra-short-term forecasting of densely distributed photovoltaic (PV) systems remains challenging because external meteorological and satellite products may not adequately…
- arXiv cs.AIresearchLarge Language Model Assisted Transportation Planning through a Differentiable User Equilibrium Layer
arXiv:2610.16140v1 Announce Type: new Abstract: Transportation planning has traditionally required substantial expertise in network modeling, traffic assignment, and optimization. As a result, strategic analyses such as…
- arXiv cs.AIresearchInteractive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction
arXiv:2610.16167v1 Announce Type: new Abstract: We propose the task of Interactive 4D Volumetric Liquid Forecasting: predicting the spatiotemporal evolution of a future dense 3D liquid velocity field conditioned on how a…
- arXiv cs.AIresearchProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts
arXiv:2610.16175v1 Announce Type: new Abstract: Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety,…
- arXiv cs.AIresearchLabel-Centric Knowledge Retrieval for Zero-Shot Text Classification
arXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit their use for large-sc…
- arXiv cs.AIresearchCorrect Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces
arXiv:2610.16191v1 Announce Type: new Abstract: A model may select the correct answer yet fail to construct it through a sequence of local decisions. We introduce Choice2Seq, a diagnostic benchmark that measures correctn…
- arXiv cs.AIresearchOneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection
arXiv:2610.16219v1 Announce Type: new Abstract: Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore e…
- arXiv cs.AIresearchScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context
arXiv:2610.16260v1 Announce Type: new Abstract: Current ASR models perform well on general benchmarks but still struggle with acoustically ambiguous words. Visual context can aid recognition in screen-based scenarios, ye…
- arXiv cs.AIresearchHardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution
arXiv:2610.16261v1 Announce Type: new Abstract: Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantization remains challenging…
- arXiv cs.AIresearchMemory-Efficient Integer-Only Training of Deep Neural Networks
arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision benchmarks retain floa…
- arXiv cs.AIresearchFON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention
arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position signals bound to the…
- arXiv cs.AIresearchNarrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment
arXiv:2610.16312v1 Announce Type: new Abstract: Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign contex…
- arXiv cs.AIresearchWhen a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models
arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target-centered, scaled co…
- arXiv cs.AIresearchChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting
arXiv:2610.16345v1 Announce Type: new Abstract: Recent advances in instruction-driven time series forecasting highlight a fundamental tension: systems must simultaneously master natural-language instruction following and…
- arXiv cs.AIresearchWorld Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models
arXiv:2610.16365v1 Announce Type: new Abstract: Video world models must generate physically plausible futures, not just realistic frames. Existing approaches typically use semantic, physical, or predictive information to…
- arXiv cs.AIresearchRetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning
arXiv:2610.16391v1 Announce Type: new Abstract: Multi-step retrosynthesis planning is often considered solved once a route to purchasable starting materials is found, but such a route should also be practical in real-wor…
- arXiv cs.AIresearchChain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking
arXiv:2610.16415v1 Announce Type: new Abstract: Industrial recommendation rankers keep scaling in width and depth to billions of parameters, but this increasingly incurs costs in parameter growth, distributed communicati…
- arXiv cs.AIresearchRAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations
arXiv:2610.16443v2 Announce Type: replace Abstract: Recent world action models draw on video generation priors to jointly predict future observations and robot actions. Adapting these priors to control requires determini…
- arXiv cs.AIresearchPXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction?
arXiv:2610.16480v1 Announce Type: new Abstract: Determining crystal structures from powder X-ray diffraction (PXRD) would enable routine characterization of newly synthesized materials, including those absent from refere…
- arXiv cs.AIresearchBoosting the Learning for Ranking Patterns
arXiv:2610.16511v1 Announce Type: new Abstract: Pattern mining is a valuable tool for exploratory data analysis, but identifying relevant patterns for a specific user is challenging. Various interestingness mea- sures ha…
- arXiv cs.AIresearchDoes the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs
arXiv:2610.16534v1 Announce Type: new Abstract: Deployed models can fail silently as the world they describe evolves. Attribution drift has served as an early warning in tabular data; we ask whether, in graph streams, a…
- arXiv cs.AIresearchMaking Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels
arXiv:2610.16552v1 Announce Type: new Abstract: An ordered visual code lets a short prefix stand in for an image, and the training loss decides what that prefix contains. Under pixel reconstruction the first bits go to t…
- arXiv cs.AIresearchAI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems
arXiv:2610.16555v1 Announce Type: new Abstract: We introduce $qt$Bench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explains given polynomial c…
- arXiv cs.AIresearchDouble-Rollout Reinforcement Learning with Sampling-based Reward Estimation
arXiv:2610.16593v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) implemented with Group Relative Policy Optimization (GRPO) has driven substantial progress in training reasoning langu…
- arXiv cs.AIresearchWhen 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction
arXiv:2610.16615v1 Announce Type: new Abstract: Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens based on text relevan…
- arXiv cs.AIresearchWeak Segmentation-Guided GAN for~Realistic Color Edition
arXiv:2610.16620v1 Announce Type: new Abstract: Editing the color of images in a realistic way finds many applications such as changing the perception of an image, data augmentation or film post processing. The design of…
- arXiv cs.AIresearchLATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation
arXiv:2610.16625v1 Announce Type: new Abstract: Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that se…
- arXiv cs.AIresearchDoes a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev
arXiv:2610.16655v1 Announce Type: new Abstract: Decision APIs that return a probability for each option are routinely used as if those probabilities were properties of the options themselves. That reading is valid only i…
- arXiv cs.AIresearchQueue-Aware Token Communications: Bridging AI Representation and Wireless Service
arXiv:2610.16730v1 Announce Type: new Abstract: The rapid advancement of foundation models and edge intelligence is transforming wireless networks from data-oriented communication systems into artificial intelligence (AI…
- arXiv cs.AIresearchSeparating Prompt Harmfulness from Interaction Safety via Partial Generation
arXiv:2610.16761v1 Announce Type: new Abstract: LLM-based information systems need safety guardrails. Most guardrails classify the prompt alone. If the prompt looks harmful, the system rejects it before any answer is gen…