AI News Archive

194 items · 50 per page

151Claude Desktop Now Supports Ollama via Third-Party Gateway19h ago0.56 152Robotics Startup Generalist Reaches $3B Valuation19h ago0.42 153Ringg Secures $10M Series A Extension for Voice AI19h ago0.32 154User Concerns Regarding Anthropic Opus 5 Verbosity and Reliability20h ago0.09 155

Entropy-Valley Length-Adaptive Decoding for Masked Diffusion Translation

20h ago

0.31

156Small VLM Performance on Qualitative Mechanical Problem-Solving Tasks20h ago0.18

157GuardianBench Evaluates Latent Contextual Risk in Embodied AI Models20h ago0.27

158Evaluating SDoH-Aware Narrative Anchoring Bias in Qwen2.5 Medical LLMs20h ago0.24

159Predicting LLM Performance on Unseen Questions via Multidimensional IRT20h ago0.21

160Cyrillic Tokenization Overhead and Mitigation via LLMLingua-220h ago0.35

161GNRS-Search for Grounded Normative Rule Generation20h ago0.18

162LLM-Based 3D Printability Assessment via Geometry Grounding20h ago0.21

163HiDiffTIR for Hierarchical Difficulty-Aware Policy Optimization20h ago0.27

164Annotator Rebuttal Attacks Degrade LLM Moderation20h ago0.24

165Agentic Context Management as a Lifecycle Architecture Problem20h ago0.34

166Community Discussion on LLM Failure Modes20h ago0.10

167HVTB Benchmark for Measuring Reward Hacking in Terminal Tasks21h ago0.31

168MemGuard Framework for Verifier-Based LLM-Agent Memory Governance21h ago0.35

169Counterfactual Ensemble Decoding for Mitigating LVLM Social Bias21h ago0.21

170ITJoint Benchmark for Query-Driven Multimodal Extraction in Long Documents21h ago0.18

171HiMA-MDD Hierarchical Multi-Agent Framework for Depression Detection21h ago0.21

172Local Hardware vs. API Token Cost Analysis21h ago0.12

173AUDITA Framework for Causal Attribution in Multi-Agent Systems21h ago0.24

174MedEventGraph-RAG for Longitudinal Clinical Event Verification21h ago0.31

175PUMA Benchmark Evaluates Multimodal Understanding in Polish Culture21h ago0.18

176MIND Model Outperforms ChatGPT in Psychiatric Patient Education21h ago0.28

177Aggregation-Aware Synthetic Text Generation for Authorship Privacy21h ago0.21

178Neural Residual Framework for Long-Term PDE Extrapolation22h ago0.18

179Secure On-Premise RAG Architecture via IBM Spyre and LinuxONE22h ago0.28

180Lexical Corruption Triggers Attention Diversion in LLM Reasoning22h ago0.21

181Open Executive Open-Source Tool Aims to Replace Corporate Executives22h ago0.10

182RAG Collapse Occurs When LLMs Retrieve Self-Authored Content22h ago0.39

183The AI Engineer Framework Automates Closed-Loop Physical Engineering Design22h ago0.32

184Prior Injection Improves Sparse-Reward RL for Vision-Language Math Reasoning22h ago0.35

185Real-TurnTurk Multimodal Dataset for Turkish Turn-Taking Prediction22h ago0.18

186Spine-Branch Coordination Optimizes Multi-Agent Computer Use23h ago0.32

187Repo2Skill-Evo Identifies Silent Decay in Agentic Software Skills23h ago0.25

188Safety Benchmark Reveals Discrepancies Between Frontier and Specialized Models23h ago0.28

189Neuro-Symbolic Pipelines Reduce Oncology Data Hallucinations23h ago0.25

190ChatGPT Work Enables Secure Browser-Based Web Automation23h ago0.61

191RO-PnR Framework Optimizes Timing for Health Misinformation Interventions23h ago0.22

192LLM Leaderboard Scores Are Highly Sensitive to Evaluation Harness Configurations23h ago0.32

193GenCoord Enables Skill-Path Commitments for Agents with Private Information23h ago0.28

194ECHO Memory Architecture Achieves 97.6% Hit@10 on LongMemEval-S23h ago0.36

← prevpage 4 / 4