AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- Hugging Face BlogresearchTrain in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0
Open-source model releases, tooling, and community updates.
- Hugging Face BlogresearchHow Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
Open-source model releases, tooling, and community updates.
- The Register AI + MLresearchAI will eat a fifth of tech budgets in 2027, but don't expect it to pay for itself
Forrester says only isolated wins are likely, while 'good enough' open-weight models soak up the tokens
- The DecoderresearchDeepmind founder Hassabis shortens AGI timeline from five to two to three years
Demis Hassabis keeps moving up his AGI timeline. The Nobel laureate and former Google Deepmind CEO now expects artificial general intelligence within two to three years, down from three to five years earlier this year. T…
- Hugging Face BlogresearchProfiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.
Open-source model releases, tooling, and community updates.
- Microsoft ResearchresearchSolving a 31-year-old grand challenge in mathematics – the KLS conjecture
For decades, a fundamental question about the difficulty of computing in high-dimensional spaces has resisted proof. New research resolves this question, removing a major theoretical obstacle to understanding the efficie…
- Hugging Face BlogresearchProtein Design with RFD4-Proteina and Hugging Face Spaces
Open-source model releases, tooling, and community updates.
- LessWrongresearchData as particles and mean field theory abound
Epistemic status: Much of this post is a reframing of known results using slightly different tooling. The framing of "data as particles" has been conceptually useful for me so it seemed useful to share. Some steps in the…
- The DecoderresearchClaude Science tackles deadly scorpion stings by designing protein binders from scratch
Anthropic's Claude independently designed protein binders targeting deadly scorpion neurotoxins. Out of more than 318,000 designs, 211 were tested in the lab. Seventeen met the criteria, and the two strongest bind extrem…
- LessWrongresearchLinkpost: Can a million AI agents create superintelligence?
https://www.noahpinion.blog/p/can-a-million-ai-agents-create-superintelligence "New post in my AI series: Can a million parallel agents create superintelligence? TLDR: More agents buy speed, but intelligence gains dimini…
- LessWrongresearchCircuit priors in NN-bayes: more results
We're posting lots of papers written with GPT-6 Astra on generalization properties of bayesian neural net learning. [1] The following picture emerges: For various reasonable priors on MLP weights, [2] the induced prior o…
- OpenAI NewsresearchUsing thousands of AI agents to uncover new leads in biological data
See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.
- Google AI BlogresearchSoutheast Asia’s digital economy to hit $368 billion
Widespread AI adoption is propelling Southeast Asia's digital economy to a projected $368 billion in 2026 and $1 trillion by 2035.
- arXiv cs.AIresearchPareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models
arXiv:2610.26904v1 Announce Type: new Abstract: Recent studies have proposed reinforcement learning with verifiable rewards (RLVR) methods that enable LLMs to generate high-quality RTL circuits from natural-language spec…
- arXiv cs.AIresearchLightCRS: Lightweight Multi-Domain Conversational Recommendation System
arXiv:2610.26948v1 Announce Type: new Abstract: Conversational recommender systems have recently adopted vision-language models to match user dialogue intents with multimodal product information. However, extending these…
- arXiv cs.AIresearchWhen Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability
arXiv:2610.26964v1 Announce Type: new Abstract: Large language models (LLMs) struggle with classical planning, but benchmarks rarely distinguish structural difficulty from the difficulty of interpreting symbolic vocabula…
- arXiv cs.AIresearchPhysical AI: Concepts, Techniques, and Challenges
arXiv:2610.27045v1 Announce Type: new Abstract: In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the fi…
- arXiv cs.AIresearchA general-purpose System One decision model for clinical records
arXiv:2610.27099v1 Announce Type: new Abstract: Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions across…
- arXiv cs.AIresearchOmni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
arXiv:2610.27103v1 Announce Type: new Abstract: Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitiga…
- arXiv cs.AIresearchEDMA: Entropy-Driven Multimodal Answering
arXiv:2610.27120v1 Announce Type: new Abstract: Multimodal question answering (MMQA) is based on integrating heterogeneous data sources, selectively leveraging relevant modalities, and ignoring distractors. Existing appr…
- arXiv cs.AIresearchMoSAIK: Motion Search with Artificial Intelligence in K-space
arXiv:2610.27156v1 Announce Type: new Abstract: Object: Motion artefacts remain a major limitation of routine two-dimensional T2-weighted turbo spin-echo (TSE) brain MRI, reducing diagnostic confidence and often necessit…
- arXiv cs.AIresearchLearned Control Variates for Rare Grid-Outage Estimation at Electric Vehicle Charging Stations
arXiv:2610.27159v1 Announce Type: new Abstract: Public charging of electric vehicles (EVs) adds a large and synchronized load to the distribution feeders. In most networks, it is rare to overload a feeder at the same tim…
- arXiv cs.AIresearchLSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental Learning
arXiv:2610.27203v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) enables models to recognize new classes over time while retaining prior knowledge, but many real-world problems are compositional, where vi…
- arXiv cs.AIresearchSparse RL Relaxation for LLM Reasoning
arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by…
- arXiv cs.AIresearchTxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event Sequences
arXiv:2610.27256v1 Announce Type: new Abstract: Analyzing merchant transaction histories requires dynamic temporal filtering, entity resolution, and aggregation over irregular event streams--operations poorly captured by…
- arXiv cs.AIresearchStronger artificial intelligence breakthroughs hasten their own exhaustion
arXiv:2610.27296v1 Announce Type: new Abstract: Progress in artificial intelligence is widely assumed to scale with effort: more researchers, papers and investment should accelerate discovery. Theories of technological g…
- arXiv cs.AIresearchWhen Does an Added Planning Capability Create Operational Value? An Observable Evidence Standard
arXiv:2610.27305v1 Announce Type: new Abstract: Industrial artificial intelligence (AI) planning systems combine predictive models, optimization logic, controls, and governance rules, but improvement in the complete poli…
- arXiv cs.AIresearchModeling Authentic Research Trajectories: A Graph View of Research Ideation
arXiv:2610.27337v1 Announce Type: new Abstract: The research idea in a published paper is rarely the project's initial idea. Between the two lies a closed-loop process in which researchers run experiments, derive insight…
- arXiv cs.AIresearchCorrecting Attribution Patching with a Few Exact Measurements
arXiv:2610.27393v1 Announce Type: new Abstract: Mechanistic interpretability asks which language model components matter for a behavior, and activation patching answers by changing one component's activation and measurin…
- arXiv cs.AIresearchWhen PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders
arXiv:2610.27397v1 Announce Type: new Abstract: Learned post-training quantization (PTQ) calibration fits quantizer parameters on a small calibration set, and for a text embedder the natural supervision is retrieval rele…
- arXiv cs.AIresearchUnified Sharp Bounds on Probabilities of Causation
arXiv:2610.27398v1 Announce Type: new Abstract: Probabilities of causation (PoCs) have developed steadily, from the binary measures first introduced by Pearl to the non-binary setting recently studied by Shu et al. As th…
- arXiv cs.AIresearchAsk to Distill: Learning to Synthesize Data for On-Policy Distillation
arXiv:2610.27450v1 Announce Type: new Abstract: On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transfer. How can…
- arXiv cs.AIresearchStructured-Token Attention for Fine-Grained mmWave Liquid Identification
arXiv:2610.27512v1 Announce Type: new Abstract: Fine-grained liquid identification requires a classifier to distinguish similar substances from compact millimeter-wave measurements. We investigate structured-token attent…
- arXiv cs.AIresearchWhen LLMs Manipulate: Measuring Behavioral, Social, and Temporal Effects
arXiv:2610.27573v1 Announce Type: new Abstract: Large language models (LLMs) can influence user trust and decision-making through subtle linguistic cues, yet the behavioral effects of manipulative outputs remain poorly q…
- arXiv cs.AIresearchMeta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
arXiv:2610.27598v1 Announce Type: new Abstract: As model parameters scale up, sparsely activated Mixture-of-Experts (MoE) approaches have become essential for model scaling. However, mainstream models currently adopt hie…
- arXiv cs.AIresearchFrom Encoding to Generation: Towards Empathetic Large Language Models
arXiv:2610.27603v1 Announce Type: new Abstract: Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an appropriate response to…
- arXiv cs.AIresearchTriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZ
arXiv:2610.27626v1 Announce Type: new Abstract: Multimodal Large Language Models show strong vision-language capabilities, yet their geometry-centric reasoning remains insufficiently understood. Existing mathematical ben…
- arXiv cs.AIresearchWhen Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design
arXiv:2610.27632v1 Announce Type: new Abstract: A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with a training-selected…
- arXiv cs.AIresearchSCODEL: Shared Canonical Ontology Definitions for Food Entity Linking and Ontology-Grounded Recipe Knowledge Graphs
arXiv:2610.27637v1 Announce Type: new Abstract: Identifying recipe entities and linking them to ontology concepts is fundamental for semantic recipe understanding. However, food mentions in recipes are often ambiguous, c…
- arXiv cs.AIresearchWhen Can LLM Reasoning Reliably Reuse Intermediate Results?
arXiv:2610.27662v1 Announce Type: new Abstract: Sampling complete solutions gives large language models more chances to solve a problem, but each attempt starts again. For tasks with several subproblems, all required ans…
- arXiv cs.AIresearchInferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networks
arXiv:2610.27668v1 Announce Type: new Abstract: Individual differences in cognitive abilities vary widely, yet the structural brain features supporting these differences remain poorly understood. Traditional brain-behavi…
- arXiv cs.AIresearchTemporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical Report
arXiv:2610.27682v1 Announce Type: new Abstract: Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the ev…
- arXiv cs.AIresearchPattern Intelligence: Unsupervised, LLM-Interpreted Discovery of Systematic Underpayment and Denial Patterns in Healthcare Revenue Cycle Management
arXiv:2610.27684v1 Announce Type: new Abstract: Healthcare providers lose substantial revenue to systematic payer underpayments and claim denials, yet identifying the recurring, correctable patterns behind them remains l…
- arXiv cs.AIresearchEASformer: Environment-Action-State Alignment for Industrial Generative Ranking
arXiv:2610.27691v2 Announce Type: replace Abstract: Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are tok…
- arXiv cs.AIresearchE8-QAT: Efficient 2-Bit Quantization-Aware Training with Implicit Lattice Codebooks
arXiv:2610.27699v1 Announce Type: new Abstract: Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar quantization encodes…
- arXiv cs.AIresearchHow Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection
arXiv:2610.27711v1 Announce Type: new Abstract: Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence (\textsc{s2s}) on binary halluc…
- arXiv cs.AIresearchHow Language Models Organize Task Information
arXiv:2610.27724v1 Announce Type: new Abstract: Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure readou…
- arXiv cs.AIresearchRSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?
arXiv:2610.27735v2 Announce Type: replace Abstract: Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has rec…
- arXiv cs.AIresearchGive the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language Models
arXiv:2610.27756v1 Announce Type: new Abstract: Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cros…
- arXiv cs.AIresearchCrystalAR: Autoregressive Modeling for Symmetric Crystal Generation
arXiv:2610.27762v2 Announce Type: replace Abstract: Deep generative modeling has achieved remarkable progress in crystal generation. Given the rich symmetries inherent in crystalline structures, recent work has sought to…