AI News Archive

173 items · 50 per page

1SCARL: Sequence Confidence-Aligned Reinforcement Learning20m ago0.19 2Hammering with Vampire in Lean20m ago0.19 3Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets20m ago0.19 4Leveraging Recourse and Size Bounds for OnlineKnapsack with Removable Items20m ago0.19 5

EventSeeColor: Learning to Reconstruct Color from Monochrome Events

20m ago

0.19

6OpenAI raises less than half of $30B target20m ago0.26

7Oracle-Guided Differentiable Safeguards for Safe Flow-Matching Robot Policies50m ago0.37

8Vision-Language Probes Disconnect from Large-Scale Retrieval Performance50m ago0.22

9LoCo Framework Localizes Concepts in Visual Autoregressive Models50m ago0.29

10Surprise-Driven Continual Learning Absorbs Falsehoods in LLMs50m ago0.26

11LiDAR-SHIELD Framework Standardizes Adversarial Testing via Dockerized HTTP Endpoints1h ago0.26

12InferD Framework Enables Deception Without Inference for AI Infrastructure1h ago0.23

13Sandman Scales Agentic RL with 11,000+ Concurrent Kubernetes Sandboxes1h ago0.37

14WorldFlow Unifies Video and 3D Motion via Mixture-of-Transformers1h ago0.29

15No more Claude Max 20x!1h ago0.31

16Autonomous Quantum Measurement with Agentic AI1h ago0.20

17Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed1h ago0.20

18DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas1h ago0.20

19CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data1h ago0.20

20Self-Supervised Latent Action-Conditioned World Modeling for Time Series1h ago0.20

21Merge and Branch Optimizes LLM Fine-Tuning for Recommendation Tasks2h ago0.33

22Echo Scales Visual Reinforcement Learning via Inverse Distillation2h ago0.30

23OrbitalGym JAX-Based Environment for Adversarial Satellite Maneuver Simulations2h ago0.20

24FARMS Framework Connects Formal Math to AI-Ready Computing Knowledge2h ago0.23

25Comparative User Experience in Web Research: ChatGPT vs Claude2h ago0.05

26Discrepancy in DeepSeek-V4.1-Flash-1017 Benchmark Comparisons2h ago0.15

27Value-Indexed Memory for Stateful Long-Context Agents2h ago0.38

28Fundamental Limits of Prefill-Based Decoding Length Prediction2h ago0.26

29Training 12M Parameter Portuguese Language Models on Single GPUs2h ago0.30

30Algebraic World Model Framework for Formal Mathematical Reasoning2h ago0.34

31OpenConjecture Dataset for Evaluating LLM Mathematical Reasoning2h ago0.23

32TACE: Two-stage Advantage and Credit Estimation for Multimodal RLVR3h ago0.30

33EnvOS: Certifying Computer-Use Agents in Dynamic Environments3h ago0.34

34Bridge-LP: Unified Graph and Language Representation for Link Prediction3h ago0.20

35SPLICE: Closing Information Gaps in Multi-Agent Systems3h ago0.30

36Glance: Unified 9B Backbone for RAG Generation and Reranking3h ago0.72

37FDSML: Supervised Metric Learning for Parameter-Aware Vision Pre-training3h ago0.40

38LOWN: Certificate-Guided Visual Routing for Efficient Diffusion VLMs3h ago0.70

39BPE Tokenizer Membership in Training Datasets via Rare Token Frequency3h ago0.27

40Supervised Fine-Tuning of Self-Concept Influences Model Attribute Retention3h ago0.20

41Sequential Monte Carlo Enables Small Models to Outperform Models 140x Larger3h ago0.38

42Autonomous Agents Formulate Research Questions via Divergent Questioning and Peer Review3h ago0.23

43vLLM now has PLE disk offload support on nightly4h ago0.16

44ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search4h ago0.20

45Retaining Repair Hypotheses for Cost-Aware Execution4h ago0.20

46Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps4h ago0.20

47HEARSAYBENCH: Can AI Navigate from Abstract Human Rights to Lived Lives?4h ago0.20

48Author-Informed Stance Detection: A Dataset and Findings4h ago0.20

49Agentic AI Optimizes Sparse-View CT Projection Selection4h ago0.31

50HEDGE Uses Hypergraph Memory for Multi-Agent Debate4h ago0.34

page 1 / 4next →