AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEvery Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution
arXiv:2605.23393v3 Announce Type: replace-cross Abstract: Interpretability methods for transformers are typically built around separate questions: which components interact, how information routes to the output, and whic…
- arXiv cs.AIresearchDeGRe: Dense-supervised Generative Reranking for Recommendation
arXiv:2605.25749v2 Announce Type: replace-cross Abstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in explori…
- arXiv cs.AIresearchWhen Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skills
arXiv:2605.25832v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape…
- arXiv cs.AIresearchA Multimodal 3D Foundation Model for Light Sheet Fluorescence Microscopy Enables Few-Shot Segmentation, Classification, and Deblurring
arXiv:2605.26026v2 Announce Type: replace-cross Abstract: Light sheet fluorescence microscopy (LSM) enables high-resolution, three-dimensional (3D) imaging of biological specimens, providing rich volumetric data for stud…
- arXiv cs.AIresearchDeep Learning-based 3D Oral Cavity Reconstruction Using 2D Intraoral Images
arXiv:2606.05998v2 Announce Type: replace-cross Abstract: Oral 3D modelling is one of the most essential stages in dentistry, and many different approaches, such as impression taking and intraoral scanning, are commonly…
- arXiv cs.AIresearch3D Oral Modelling with Improved Vertex Distribution Using Matching-Based Learning
arXiv:2606.07907v2 Announce Type: replace-cross Abstract: In our previous work, a deep learning-based framework for 3D intraoral reconstruction was proposed. The model directly predicts explicit 3D point cloud coordinate…
- arXiv cs.AIresearchJoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
arXiv:2606.14777v2 Announce Type: replace-cross Abstract: Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor, an expression flickers across a video call, or a product a view…
- arXiv cs.AIresearchBreaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
arXiv:2606.31825v2 Announce Type: replace-cross Abstract: Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-ce…
- arXiv cs.AIresearchSOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction
arXiv:2607.04119v2 Announce Type: replace-cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. However, exis…
- arXiv cs.AIresearchSechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
arXiv:2607.18290v4 Announce Type: replace-cross Abstract: In recent years KolmogorovArnold Networks KANs have attracted increasing attention due to their effectiveness in machine learning and scientific computing offerin…
- arXiv cs.AIresearchA Multi-level Information Integration Framework for Physically Verifiable Fault Diagnosis of Rotating Machinery
arXiv:2607.22797v2 Announce Type: replace-cross Abstract: Integrating multi-level information, from physical models through data-driven diagnostics to natural language reasoning, into verifiable decision chains is a grow…
- arXiv cs.AIresearchWiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling
arXiv:2608.02829v5 Announce Type: replace-cross Abstract: Model families are trained size by size. Can a pretrained large model instead be converted into a smaller sibling? We characterize the 1.4B->410M conversion in Py…
- arXiv cs.AIresearchQ-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning
arXiv:2608.04452v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) can miss fine details in a full image that they recognize in a closer view. Recovering this evidence requires deciding wh…
- arXiv cs.AIresearchA Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning
arXiv:2608.07335v4 Announce Type: replace-cross Abstract: Replay-free parallelized Q-learning removes the large experience replay buffers and target networks used by conventional deep Q-learning, but the role of network…
- arXiv cs.AIresearchToo Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
arXiv:2608.17965v4 Announce Type: replace-cross Abstract: Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log anomaly detect…
- arXiv cs.AIresearchJ-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data
arXiv:2608.26582v2 Announce Type: replace-cross Abstract: Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. Wh…
- arXiv cs.AIresearchAero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning
arXiv:2608.28578v2 Announce Type: replace-cross Abstract: Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce…
- arXiv cs.AIresearchA Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension
arXiv:2609.00322v2 Announce Type: replace-cross Abstract: Can an artificial intelligence (AI) generate a scientific hypothesis outside a human collaborator's active hypothesis space (AHS), and can human-AI research be or…
- arXiv cs.AIresearchHow broad is that claim? Mapping Generalisation in NLP Research
arXiv:2609.14770v2 Announce Type: replace-cross Abstract: Generalisations are common in scientific communication, even though they are semantically ambiguous. An automated method is needed to identify and categorise clai…
- arXiv cs.AIresearchNeural-Network Solutions to Real-Space Charge Density and Generalization
arXiv:2609.14906v4 Announce Type: replace-cross Abstract: The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system, such that a…
- BBC TechnologyresearchX-planes: Are they needed in the new era of drones?
Where do America's X-plane projects fit in an era of cheap drones?
- LessWrongresearchAI in research and publishing (Sep 2026)
epistemic status: I have low confidence in these findings, primarily because my anecdotal experience (I'm a researcher) is that AI usage in research has been changing more quickly in the recent months, so analysis of the…
- LessWrongresearchIncreasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer
Paper: Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer TL;DR: Maia-3 is a transformer-based chess model that takes Elo (the standard metric for competitive chess skill) as an input t…
- The DecoderresearchTop AI experts badly underestimated how fast the field is moving, study finds
Leading AI experts have consistently underestimated how fast AI is advancing, according to the Forecasting Research Institute. AI reached gold-medal level at the International Mathematical Olympiad five years ahead of th…
- The DecoderresearchAnthropic says Claude discovered a new enzyme system, but CRISPR researchers call it routine genome mining
Anthropic's AI model Claude found a previously unknown enzyme system in DNA databases, doing most of the analysis on its own. The article Anthropic says Claude discovered a new enzyme system, but CRISPR researchers call…
- The DecoderresearchAI performance costs are falling faster than those of any previous technology
AI is hitting a fixed benchmark performance level at a rapidly falling cost. Epoch AI measures a price decline of about 13x per year. After stripping out hardware gains and competition, MIT puts annual algorithmic progre…
- Latent SpaceresearchFoundries vs Navigators: Lowering the Cost of Science
Guest Post: In science, thinking has gotten cheap but doing has not. This asymmetry is reshaping how research companies operate, largely inconspicuously.
- NVIDIA BlogresearchHow Open Science Can Help Researchers Prepare for the Next Pandemic
When COVID-19 emerged, scientists had a crucial advantage: Decades of prior research on coronaviruses meant they understood the virus’ key proteins well enough to design vaccines in record time. The next pandemic may not…
- LessWrongresearchRethinking Credit and Recognition in Mathematics in the Age of AI
This text follows from some thoughts I have had on the current impact of AI on mathematics and on the reactions I have seen. It is also a follow-up to my first essay. It is based on one premise: there exists a credit sys…
- Google ResearchresearchBehind Project Suncatcher, our moonshot to put AI in space
Learn about Project Suncatcher, how we’re testing hardware survival for space, designing cooling systems for AI chips, and more.
- LessWrongresearcha recurrent llm is quite easy to interpret but very hard to steer
TLDR; Ouro-1.4b-thinking is broadly interpretable with logit lenses and linear probes. It's also steerable but does 'clean' foreign concepts out of the residual stream if they're injected before the last loop. This could…
- LessWrongresearcha recurrent llm is quite easy to interpret but complex to steer
TLDR; Ouro-1.4b-thinking is broadly interpretable with logit lenses and linear probes. It's also steerable but does 'clean' foreign concepts out of the residual stream if they're injected before the last loop. This could…
- LessWrongresearchAnthropic shares an exciting result in enzyme discovery - and an exercise in public's perception of science and AI
Disclaimer: I'm not affiliated with Anthropic, these are my own thoughts as a former wet lab chemist currently working in chem-biosecurity and AI evals. I appreciate the complexity of scientific research and genuinely be…
- arXiv cs.AIresearchWhich Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment
arXiv:2609.26929v1 Announce Type: new Abstract: People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable models that can bala…
- arXiv cs.AIresearchEscaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution
arXiv:2609.26952v1 Announce Type: new Abstract: Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-wor…
- arXiv cs.AIresearchSame evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts
arXiv:2609.26986v1 Announce Type: new Abstract: For multimodal large language models, when images or speech conflict with accompanying text, measured text reliance can entangle modality preference with evidence position.…
- arXiv cs.AIresearchAre Stated Reasoning Steps Causally Load-Bearing?
arXiv:2609.27038v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfulness metrics have b…
- arXiv cs.AIresearchMath Reasoning in LLMs is Organized by Approach, Not Topic
arXiv:2609.27041v2 Announce Type: replace Abstract: Mathematical reasoning benchmarks are typically organized by topic, but language models may organize their internal computation by reusable reasoning approach instead.…
- arXiv cs.AIresearchPolicy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit
arXiv:2609.27087v1 Announce Type: new Abstract: Organizations increasingly use LLMs for policy, compliance, risk, and operational decision support, requiring evidence validation, review routing, version control, and audi…
- arXiv cs.AIresearchProvably Complete Generalized Planning with LLMs
arXiv:2609.27105v1 Announce Type: new Abstract: Generalized planning aims to compute a plan that solves all instances of a planning domain. Recent work has used LLMs to automatically generate and debug such generalized p…
- arXiv cs.AIresearchEnhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training
arXiv:2609.27197v1 Announce Type: new Abstract: Minimum Risk Training (MRT) enables neural machine translation models to directly optimize sequence-level evaluation metrics instead of relying only on token- level maximum…
- arXiv cs.AIresearchXLOG: A CUDA-Native Engine for Neurosymbolic Integration
arXiv:2609.27203v1 Announce Type: new Abstract: xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world views through a typed…
- arXiv cs.AIresearchHunyuan-A13B Technical Report
arXiv:2609.27284v1 Announce Type: new Abstract: We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billi…
- arXiv cs.AIresearchPotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks
arXiv:2609.27288v2 Announce Type: replace Abstract: The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI models. Yet standard…
- arXiv cs.AIresearchSparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins
arXiv:2609.27290v1 Announce Type: new Abstract: Short-horizon forecasts of atmospheric temperature are needed to support climate-aware digital-twin systems, but such forecasts must be produced where thermal observations…
- arXiv cs.AIresearchAlignment Inertia: Auditing the Durability of Training Data Influence Through Policy Override Resistance
arXiv:2609.27333v1 Announce Type: new Abstract: Platform operators increasingly rely on system prompts and fine-tuning to govern model behavior, yet it remains unclear how reliably these interventions override behavior i…
- arXiv cs.AIresearchCART: Closed-Loop Adaptive Red Teaming for Large Language Models
arXiv:2609.27336v1 Announce Type: new Abstract: Automated red teaming often replays a fixed set of prompts, which measures known risks but cannot learn from failures found during testing. We present CART (Closed-Loop Ada…
- arXiv cs.AIresearchNot What You Meant: Can LLMs Follow a Specified Negation Semantics?
arXiv:2609.27517v1 Announce Type: new Abstract: Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force --…
- arXiv cs.AIresearchBiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport
arXiv:2609.27615v1 Announce Type: new Abstract: In multimodal emotion recognition (MER), human affective states are inferred by integrating complementary cues from multiple modalities. In audio-text MER, affective cues a…
- arXiv cs.AIresearchSHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
arXiv:2609.27621v2 Announce Type: replace Abstract: Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework…