HACKOBAR_
ABOUT
AI News Archive
196 items · 50 per page
101
Quantization Reduces LLM Self-Explanation Quality and Faithfulness
16h ago
0.31
102
QC-T2I-Bench Framework for Fine-Grained Text-to-Image Evaluation
16h ago
0.27
103
Llama.cpp Adaptive Speculation Increases Inference Speed by 50%
16h ago
0.18
104
Qwen3.8-27B Fully Quantized to NVFP4 via QUASAR
16h ago
0.52
105
Prompt Format Significantly Influences AI Preference Measurements
16h ago
0.27
106
ExTS Tree-Search Policy Optimizes Budget-Constrained Agentic Search
16h ago
0.44
107
AgentWorld Framework Evaluates Agentic IR via Personality Simulation
16h ago
0.35
108
LVLMs Struggle with Interactive Visual Grounding Tasks
16h ago
0.31
109
LLMs Underrepresent Minimal Responses in Counseling Dialogues
16h ago
0.24
110
Recursive reasoning operators improve agentic performance via branching and pruning
17h ago
0.40
111
Two-stage framework mitigates exploration bias in multi-instruction RL training
17h ago
0.31
112
Relative timestamp representation improves temporal alignment in SpeechLLMs
17h ago
0.28
113
Minima-KV achieves 3.5x KV cache compression with mixed-format paged attention
17h ago
0.44
114
MARS Multi-Specialist Relay System for Competitive Programming
17h ago
0.56
115
Rubric-Based Reward Framework for Grounded QA Alignment
17h ago
0.44
116
AI Agent Autonomy Degrades Human Oversight Capacity
17h ago
0.32
117
LT-MKT Method for Multi-Domain Knowledge Tracing
17h ago
0.24
118
Auditing XAI Robustness and Fidelity via Trust Score Framework
17h ago
0.28
119
Characterizing Serving Hardware Requirements for Masked Diffusion LLMs
18h ago
0.40
120
FLARE: Evaluating the Economic Value of AI in Healthcare
18h ago
0.24
121
Provenance-Guided Incremental Learning for Rule-Induced Concept Shift
18h ago
0.28
122
LongRCA Bench: Diagnosing Long-Horizon Agent Failures
18h ago
0.55
123
Entropy-Valley: Length-Adaptive Decoding for Diffusion MT
18h ago
0.48
124
BPCO: Stabilizing Critic Optimization in Group RL
18h ago
0.62
125
OPDVR: Seamlessly Combining OPD and RLVR
18h ago
0.69
126
CAFE: Co-Evolving Agent and Feedback for Search Agents
18h ago
0.62
127
TorchMorph: CUDA-Accelerated Morphological Transforms for PyTorch
18h ago
0.76
128
G2WEngine: Removing Gameplay UI for World Model Training
18h ago
0.62
129
Smart Glasses as First-Person Intelligence Platforms
18h ago
0.31
130
LAION-BVD: 10-Million-Hour Open Video Dataset
18h ago
0.76
131
Meta^n: Recursive Self-Improvement via Fixed Meta-Operations
18h ago
0.62
132
Recuris: Recursive Memory Architecture for Long-Horizon Agents
18h ago
0.69
133
Audit Tool Detects Causality Leaks in Sequence Models
18h ago
0.69
134
WeMM-Embedding: Multimodal Embedding Family up to 9B Parameters
18h ago
0.76
135
OraRL: Efficient Video MLLM Post-training via Oracle Rollouts
18h ago
0.69
136
Composable Trust Infrastructure for Manufacturing Knowledge Graphs
18h ago
0.20
137
Emergent vs. Computed Functions in Cognitive Architectures
18h ago
0.27
138
Agents Construct Human Stereotypes in Open Social Networks
18h ago
0.18
139
Multi-Agent LLM Orchestration for Explainable AI Selection
18h ago
0.24
140
Gemini Leads Blind Student Preference Tests for Essay Writing
18h ago
0.26
141
SSKG Method Fixes LLM Student Simulation Accuracy Issues
19h ago
0.24
142
Multi-Role RL Improves Symbolic Planning Success to 70.8%
19h ago
0.34
143
TA-SPA Enables Transferable Jailbreak Attacks on Multimodal Models
19h ago
0.31
144
MEMONDEMAND Manages Large-Scale Enterprise Data for RAG
19h ago
0.27
145
HERO Framework Optimizes Long-Term Agent Memory via Heterogeneous Graphs
19h ago
0.27
146
Claude Desktop Now Supports Ollama via Third-Party Gateway
19h ago
0.56
147
Robotics Startup Generalist Reaches $3B Valuation
19h ago
0.42
148
Ringg Secures $10M Series A Extension for Voice AI
19h ago
0.32
149
User Concerns Regarding Anthropic Opus 5 Verbosity and Reliability
19h ago
0.09
150
Entropy-Valley Length-Adaptive Decoding for Masked Diffusion Translation
19h ago
0.31
← prev
page 3 / 4
next →