HACKOBAR_
ABOUT
AI News Archive
185 items · 50 per page
1
ReCAP Uses Persistent Context Graphs for Efficient LLM Agent Memory
25m ago
0.44
2
LEAP Framework Decouples Evidence Retrieval from Long Audio-Video Reasoning
25m ago
0.28
3
OverForge Hierarchical Architecture Separates Strategic and Tactical Agent Reasoning
25m ago
0.31
4
EvoDuet Optimizes LLM Web Search and Task Solving Co-Evolution
25m ago
0.35
5
RIGS Framework Enables Instruction-Conditioned Retrosynthesis Steering
25m ago
0.28
6
Mistral Targets Performance Parity with U.S. AI Labs
55m ago
0.13
7
COVER: Coverage-Aware Multilingual Unlearning for LLMs
55m ago
0.40
8
OverdoseMoE: Multi-Expert Framework for Opioid Overdose Risk
55m ago
0.36
9
AdaGEPA: Adaptive Feedback Allocation for Prompt Optimization
55m ago
0.32
10
Impact of Lexical Ambiguity and Underspecification on LLM Training
55m ago
0.28
11
Scaling Laws for Wild AI-Generated Web Text in Pretraining
55m ago
0.44
12
OPSRD Enables On-Policy Self-Distillation Using Expert Role Prompting
1h ago
0.45
13
ArchitectureIQ Benchmark Measures LLM Training Intuition vs Human Experts
1h ago
0.28
14
SpeechConversationBench Evaluates Multi-Turn Reasoning in Speech-to-Speech Models
1h ago
0.40
15
OSWorld-Science Benchmark for Computer-Use Agents in Scientific Workflows
1h ago
0.36
16
BiFE for Efficient CPU-Only Branching Policies via LLMs
1h ago
0.18
17
Framework for Distilling Knowledge in Complex Agentic Systems
1h ago
0.21
18
Spectral Optimization for Controlling Safety Instruction Strength
1h ago
0.24
19
FedLAFP Framework for Personalized Federated Fine-Tuning
1h ago
0.27
20
Last-Chance Policy Identification for Agents Under Resource Depletion
1h ago
0.21
21
OpenAI Agents Escaped Sandboxes via Zero-Day Vulnerabilities
1h ago
0.35
22
SAKI Method Optimizes On-Policy Distillation via Maximal-Coupling-Routed Supervision
2h ago
0.24
23
ARCagent Calibrates Clinical RAG for Conflicting Medical Guidelines
2h ago
0.27
24
Self-Correction Trade-offs in 29 Open-Weight LLMs
2h ago
0.31
25
Attuner Enables Recomputation-Free KV Cache Reuse via Query-Side Adaptation
2h ago
0.34
26
JEV Model Cultural Alignment Shifts with Persona and Language
2h ago
0.21
27
Counterfactual Diagnostics Separate Visual Sensitivity from Claim Persistence in LVLMs
2h ago
0.24
28
HyperZip Uses Diffusion LLMs and Hypernetworks for Faster Compression
2h ago
0.21
29
Identifying Attention Heads Responsible for LLM Sycophancy
2h ago
0.27
30
ContextProgress-Bench Evaluates Progress Reward Models in Long-Horizon Tasks
2h ago
0.18
31
LLM-Guided Pruning Fixes Geometry-Semantic Mismatch in ANN Graphs
2h ago
0.21
32
Factor Analysis of 1,618 Models Reveals Partial Intelligence Interpretability
3h ago
0.18
33
HeurEvo Automates Hybrid Solver-Augmented Heuristics via Co-Evolution
3h ago
0.21
34
LUDI Framework Scales Diffusion Language Models with Per-Token Embeddings
3h ago
0.35
35
RankBuffer Optimizes Open-Ended Generation via Reusable Quality Buffers
3h ago
0.27
36
StateTape Rewrites Coding Agent Context via Repository State Changes
3h ago
0.31
37
FinRT Framework Automates Adversarial Prompt Generation for Finance Models
3h ago
0.31
38
CoRe Framework Mitigates Latent Reward Hacking in Video Diffusion
3h ago
0.28
39
evalstats Tooling Provides Calibrated Statistical Inference for LLM Judges
3h ago
0.24
40
TrustSwap Reveals Source-Trust Shortcuts in Fact-Checking RL Agents
3h ago
0.28
41
OLIVE Distillation Method Improves Reasoning Performance via Teacher Continuations
3h ago
0.35
42
MemFold Optimizes Fixed-Budget Soft Memory for Long-Context Personalization
4h ago
0.31
43
LLMs Suffer Reliability Issues with Non-Canonical Multi-Valued Relations
4h ago
0.21
44
BreakingWeb Benchmarks Browser-Use Agents via Controlled Environment Interventions
4h ago
0.24
45
AdaLCPI Attack Reconstructs Indirect Prompt Injections from Fragments
4h ago
0.35
46
CineSubBench Evaluates Long-Context Multilingual Film Understanding
4h ago
0.18
47
Framework Desktop Preorders Open for AMD Ryzen AI Max 400 Series
4h ago
0.06
48
Dense Retrievers Exhibit Political and Dialect Bias in Query Responses
4h ago
0.35
49
PhenoAIR Uses Multi-Agent Reasoning for Cell Painting MOA Prediction
4h ago
0.24
50
FigAct Transforms Static Scientific Figures Into Interactive Visual Presentations
4h ago
0.31
page 1 / 4
next →