HACKOBAR_ABOUT

AI News Archive

196 items · 50 per page
101Quantization Reduces LLM Self-Explanation Quality and Faithfulness16h ago0.31102QC-T2I-Bench Framework for Fine-Grained Text-to-Image Evaluation16h ago0.27103Llama.cpp Adaptive Speculation Increases Inference Speed by 50%16h ago0.18104Qwen3.8-27B Fully Quantized to NVFP4 via QUASAR16h ago0.52105
Prompt Format Significantly Influences AI Preference Measurements
16h ago
0.27
106ExTS Tree-Search Policy Optimizes Budget-Constrained Agentic Search16h ago0.44
107AgentWorld Framework Evaluates Agentic IR via Personality Simulation16h ago0.35
108LVLMs Struggle with Interactive Visual Grounding Tasks16h ago0.31
109LLMs Underrepresent Minimal Responses in Counseling Dialogues16h ago0.24
110Recursive reasoning operators improve agentic performance via branching and pruning17h ago0.40
111Two-stage framework mitigates exploration bias in multi-instruction RL training17h ago0.31
112Relative timestamp representation improves temporal alignment in SpeechLLMs17h ago0.28
113Minima-KV achieves 3.5x KV cache compression with mixed-format paged attention17h ago0.44
114MARS Multi-Specialist Relay System for Competitive Programming17h ago0.56
115Rubric-Based Reward Framework for Grounded QA Alignment17h ago0.44
116AI Agent Autonomy Degrades Human Oversight Capacity17h ago0.32
117LT-MKT Method for Multi-Domain Knowledge Tracing17h ago0.24
118Auditing XAI Robustness and Fidelity via Trust Score Framework17h ago0.28
119Characterizing Serving Hardware Requirements for Masked Diffusion LLMs18h ago0.40
120FLARE: Evaluating the Economic Value of AI in Healthcare18h ago0.24
121Provenance-Guided Incremental Learning for Rule-Induced Concept Shift18h ago0.28
122LongRCA Bench: Diagnosing Long-Horizon Agent Failures18h ago0.55
123Entropy-Valley: Length-Adaptive Decoding for Diffusion MT18h ago0.48
124BPCO: Stabilizing Critic Optimization in Group RL18h ago0.62
125OPDVR: Seamlessly Combining OPD and RLVR18h ago0.69
126CAFE: Co-Evolving Agent and Feedback for Search Agents18h ago0.62
127TorchMorph: CUDA-Accelerated Morphological Transforms for PyTorch18h ago0.76
128G2WEngine: Removing Gameplay UI for World Model Training18h ago0.62
129Smart Glasses as First-Person Intelligence Platforms18h ago0.31
130LAION-BVD: 10-Million-Hour Open Video Dataset18h ago0.76
131Meta^n: Recursive Self-Improvement via Fixed Meta-Operations18h ago0.62
132Recuris: Recursive Memory Architecture for Long-Horizon Agents18h ago0.69
133Audit Tool Detects Causality Leaks in Sequence Models18h ago0.69
134WeMM-Embedding: Multimodal Embedding Family up to 9B Parameters18h ago0.76
135OraRL: Efficient Video MLLM Post-training via Oracle Rollouts18h ago0.69
136Composable Trust Infrastructure for Manufacturing Knowledge Graphs18h ago0.20
137Emergent vs. Computed Functions in Cognitive Architectures18h ago0.27
138Agents Construct Human Stereotypes in Open Social Networks18h ago0.18
139Multi-Agent LLM Orchestration for Explainable AI Selection18h ago0.24
140Gemini Leads Blind Student Preference Tests for Essay Writing18h ago0.26
141SSKG Method Fixes LLM Student Simulation Accuracy Issues19h ago0.24
142Multi-Role RL Improves Symbolic Planning Success to 70.8%19h ago0.34
143TA-SPA Enables Transferable Jailbreak Attacks on Multimodal Models19h ago0.31
144MEMONDEMAND Manages Large-Scale Enterprise Data for RAG19h ago0.27
145HERO Framework Optimizes Long-Term Agent Memory via Heterogeneous Graphs19h ago0.27
146Claude Desktop Now Supports Ollama via Third-Party Gateway19h ago0.56
147Robotics Startup Generalist Reaches $3B Valuation19h ago0.42
148Ringg Secures $10M Series A Extension for Voice AI19h ago0.32
149User Concerns Regarding Anthropic Opus 5 Verbosity and Reliability19h ago0.09
150Entropy-Valley Length-Adaptive Decoding for Masked Diffusion Translation19h ago0.31
← prevpage 3 / 4next →