AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFSCE: A Target-Aware Frequency-Spatial Collaborative Enhancement Framework for Noise-Resilient SAR ATR
arXiv:2603.21565v3 Announce Type: replace-cross Abstract: Synthetic aperture radar automatic target recognition (SAR ATR) is severely challenged by coherent speckle noise, whose interference can be progressively amplifie…
- arXiv cs.AIresearchSoftmax gradient policy for variance minimization and risk-averse multi armed bandits
arXiv:2604.00241v2 Announce Type: replace-cross Abstract: Algorithms for the Multi-Armed Bandit (MAB) problem play a central role in sequential decision-making and have been extensively explored both theoretically and nu…
- arXiv cs.AIresearchLitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape
arXiv:2604.02600v3 Announce Type: replace-cross Abstract: Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively…
- arXiv cs.AIresearchTiAb Review Plugin: A Browser-Based Tool for AI-Assisted Study Selection in Systematic Reviews
arXiv:2604.08602v2 Announce Type: replace-cross Abstract: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills, and full-text screening has remained outside the sco…
- arXiv cs.AIresearchJoint Interference Detection and Identification via Adversarial Multi-task Learning
arXiv:2604.08607v2 Announce Type: replace-cross Abstract: Precise interference detection and identification are crucial for enhancing the survivability of communication systems in non-cooperative wireless environments. W…
- arXiv cs.AIresearchEA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
arXiv:2605.06192v2 Announce Type: replace-cross Abstract: Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world…
- arXiv cs.AIresearchProteinJEPA: Latent prediction improves protein language model pretraining
arXiv:2605.07554v2 Announce Type: replace-cross Abstract: Protein language models are trained primarily with masked language modeling (MLM), which predicts masked amino-acid identities. Joint-embedding predictive archite…
- arXiv cs.AIresearchDreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
arXiv:2605.11750v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly escalate into…
- arXiv cs.AIresearchTukaBench: A Culturally Grounded Jailbreak Benchmark for African Languages
arXiv:2606.01322v2 Announce Type: replace-cross Abstract: Safety evaluation of Large Language Models (LLMs) remains heavily English-centric, leaving Low-Resource Languages (LRLs), particularly African ones, critically un…
- arXiv cs.AIresearchRouting-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models
arXiv:2606.10338v2 Announce Type: replace-cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored. Unlike den…
- arXiv cs.AIresearchIB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation
arXiv:2607.09133v3 Announce Type: replace-cross Abstract: While large-scale text-to-image generative models have achieved unprecedented visual performance, their inherent reliance on multi-step iterative solvers incurs s…
- arXiv cs.AIresearchNever Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection
arXiv:2607.14236v3 Announce Type: replace-cross Abstract: Pretrained vision-language-action (VLA) policies provide strong language-conditioned manipulation knowledge, but they remain largely vision-driven and can struggl…
- arXiv cs.AIresearchBenchmarking Text-to-SQL under Role-Based Access Control
arXiv:2607.22115v2 Announce Type: replace-cross Abstract: Given a database S and a natural language question Q, text-to-SQL systems aim to generate an SQL query that correctly answers Q when executed against S. Currently…
- arXiv cs.AIresearchPhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us
arXiv:2609.06080v2 Announce Type: replace-cross Abstract: Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years, but heterogeneous analyses are…
- arXiv cs.AIresearchBIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors
arXiv:2609.08673v2 Announce Type: replace-cross Abstract: Vision-based tactile sensors provide high-resolution contact information for robotic perception and contact-rich manipulation, advancing embodied intelligence thr…
- arXiv cs.AIresearchRAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
arXiv:2609.14856v2 Announce Type: replace-cross Abstract: Semantic watermarks for diffusion models embed ownership information into the generative process while preserving perceptual quality, but Gaussian-Shading extract…
- arXiv cs.AIresearchWorld Models for Cross-Machine CNC Transfer under Partial Sensor Overlap
arXiv:2609.16071v2 Announce Type: replace-cross Abstract: Industrial world models must move between machines whose dynamics, sensing interfaces and command conventions differ. This study asks whether a command-conditione…
- LessWrongresearchThoughts on the persona selection model
As AIs have become more "RLVR-brained," there's been some commentary on what this means for the persona selection model (PSM). This post presents some loose thoughts on that topic. A rough summary of my opinions: PSM is…
- Apple Machine Learning ResearchresearchCompressing Streaming Neural Audio Encoders via Latent-Space Distillation
System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the l…
- Apple Machine Learning ResearchresearchA Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
Semi-supervised federated learning (SSFL) trains models on clients’ unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particu…
- NVIDIA Developer BlogresearchEfficient MoE Training for Biological Foundation Models
As language models grow, scaling dense architectures becomes increasingly expensive. In a dense transformer, every token passes through every layer, so adding...
- AI Stack ExchangeresearchHow can I convert intuition into feature vectors for computing similarity/closeness?
It’s kind of a broad question, but let me narrow it down to one specific use-case/example I'm currently working on / interested in: Finding "closeness" or "similarity" of writing system glyphs (script characters), like a…
- Hugging Face BlogresearchHow to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows
Open-source model releases, tooling, and community updates.
- AI BusinessresearchLack of training data stifling humanoid bot development
AI models train on information available on the internet. Robots can’t do that.
- AI BusinessresearchNvidia-backed Skild AI teaches robots new tasks from a single video
The development adds to the rising momentum toward general-purpose robots and the real-world deployment of physical AI.
- AI Stack ExchangeresearchWhy does mode collapse happen in knowledge distillation?
In regards specifically to mode collapse in the DINO head, I am not asking exactly why the teacher and student eventually gravitate towards producing the same output as thats one way to make the loss minimal even if its…
- LessWrongresearchThermodynamics and Objects
2.3.1 Varied stable objects 2.3.1.1 Life as we know it requires a world which is intelligible and predictable, but also rich enough to support the complex mechanisms needed for cognition. Furthermore, given the definitio…
- The Verge AIresearchAnthropic’s biolab made a discovery it’s comparing to Crispr
Anthropic says its AI Claude has "autonomously discovered" a new enzyme system similar to machinery behind the powerful gene-editing tool Crispr. It's the first result from Anthropic's newly-launched wet lab and an early…
- NVIDIA Developer BlogresearchHow SWE-Serve Exposes the Gap Between Local Tests and Live Serving
An AI coding agent’s patch can pass tests yet fail when the server loads a real model and handles requests. Evaluating changes to inference-serving software...
- Microsoft ResearchresearchOffloaded inference for real-world physical AI robotics
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanc…
- LessWrongresearchWorkspaceBench: Evaluating Interpretability Methods for the Global Workspace
TL;DR We introduce WorkspaceBench, a set of evaluations for how well an activation-to-text tool can read the contents of the “global workspace” of a model, i.e. the intermediate variables during a forward pass. The bench…
- arXiv cs.AIresearchDo Synthetic Personas Predict Real Audience Response? A Sim-to-Real Study Where a No-Persona Baseline Beats Persona-Based Copy Simulation
arXiv:2609.25010v1 Announce Type: new Abstract: Marketers increasingly use large language models (LLMs) as "synthetic personas" to predict how an audience will react to a piece of copy before it ships, encouraged by evid…
- arXiv cs.AIresearchDo Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization
arXiv:2609.25013v1 Announce Type: new Abstract: Tabular foundation models have recently shown strong potential for structured biomedical data analysis. Among them, TabPFN has emerged as an effective approach for low-data…
- arXiv cs.AIresearch4DGS-JEPA: Temporally Compositional Joint-Embedding Prediction for Dynamic Gaussian Splatting
arXiv:2609.25036v1 Announce Type: new Abstract: Dynamic Gaussian Splatting provides an explicit representation of evolving 3D scenes, but existing approaches are primarily optimized for reconstruction, future-state gener…
- arXiv cs.AIresearchAn Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction
arXiv:2609.25088v1 Announce Type: new Abstract: Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these objectives as com- peting…
- arXiv cs.AIresearchOvis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
arXiv:2609.25165v1 Announce Type: new Abstract: In this report, we introduce \textbf{Ovis-Embedding}, a state-of-the-art omni-modal embedding family built on native integration of text, image, video, and audio. Instead o…
- arXiv cs.AIresearchX-Planner: Event-Structured Task Planning for Embodied Intelligence
arXiv:2609.25187v2 Announce Type: replace Abstract: Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems often leave this int…
- arXiv cs.AIresearchMedGate-Fusion: Integrating First-Encounter Semantic Narratives and Physiological Biomarkers for Prospective Stroke Risk Stratification
arXiv:2609.25272v1 Announce Type: new Abstract: Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narrati…
- arXiv cs.AIresearchAttention as a Routing Graph: Live Circuit Extraction from a Single Forward Pass
arXiv:2609.25285v1 Announce Type: new Abstract: Finding circuits in language models usually means running many careful interventions. We try something simpler: treat attention as a routing map from one forward pass, keep…
- arXiv cs.AIresearchPotential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing
arXiv:2609.25303v1 Announce Type: new Abstract: Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revise…
- arXiv cs.AIresearchClarification Is Not Correction: LLMs Fail to Let Go
arXiv:2609.25337v1 Announce Type: new Abstract: Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem…
- arXiv cs.AIresearchFrom Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought
arXiv:2609.25366v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch…
- arXiv cs.AIresearchRobust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures
arXiv:2609.25400v1 Announce Type: new Abstract: Failure-based textual knowledge distillation aims to discover gaps in a model's knowledge by examining its task errors. The distilled knowledge can be useful for the reason…
- arXiv cs.AIresearchEfficient Iterative Retrieval with Heterogeneous Batching
arXiv:2609.25405v1 Announce Type: new Abstract: Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughpu…
- arXiv cs.AIresearchFrom Offline Proxies to Online Decisions: A Layered Engagement Evaluation Framework for Conversational AI
arXiv:2609.25408v1 Announce Type: new Abstract: Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an…
- arXiv cs.AIresearchRollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions
arXiv:2609.25463v1 Announce Type: new Abstract: Reasoning-oriented reinforcement learning enables large language models to solve mathematical, coding, and other multi-step tasks, but shifts a substantial portion of the t…
- arXiv cs.AIresearchReal-Time Hand Gesture Recognition for OpenXR Using Transformer-Based Machine Learning
arXiv:2609.25466v1 Announce Type: new Abstract: Hand gesture recognition is a key component in human-computer interaction (HCI), enabling intuitive interfaces for applications in gaming, virtual reality (VR), robotics, a…
- arXiv cs.AIresearchRAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation
arXiv:2609.25469v1 Announce Type: new Abstract: Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable external knowledge, ye…
- arXiv cs.AIresearchSpectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing
arXiv:2609.25474v1 Announce Type: new Abstract: Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate comp…
- arXiv cs.AIresearchQueer inclusion in speech datasets: An audit and taxonomy of practical tensions
arXiv:2609.25491v1 Announce Type: new Abstract: In this paper, we examine speech datasets for their inclusion of LGBTQIA+, or queer, voices and provide a taxonomy of tensions to better understand why there is a lack of s…