HACKOBAR_
ABOUT
AI News Archive
205 items · 50 per page
151
SafeMath Addresses Toxicity in Mathematical Word Problems
20h ago
0.31
152
TPSO Improves Diffusion Model Image Diversity Without Retraining
20h ago
0.27
153
Test-Time Scaling via Agent Breadth and Depth
20h ago
0.60
154
LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
20h ago
0.24
155
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
20h ago
0.24
156
OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models
20h ago
0.24
157
Evaluating Perspectival Biases in Cross-Modal Retrieval
20h ago
0.24
158
I can't do Opus 5 anymore. Every time I talk with it and try to read it, I literally get so confused. Has anyone figured out how to not make it weird to work with?
21h ago
0.14
159
FIA Framework Automates Multimodal Credit Card Fraud Investigations
21h ago
0.25
160
CFKD-AFN Improves Treatment Prediction via Dual-Channel Knowledge Distillation
21h ago
0.30
161
FRAMEWORKERS Multi-Agent Framework for Dynamic AI Video Production
21h ago
0.31
162
Vision-Enabled Models Improve Autonomous Coding via Visual Error Detection
21h ago
0.22
163
Estimating Watermark Proportions in Mixed Human-AI Text
21h ago
0.28
164
RNop Transformer Resolves mRNA Optimization Trade-offs via Knowledge-Infusion
21h ago
0.44
165
StructSynth Uses Dependency Graphs as Generation Plans for Tabular Data
21h ago
0.36
166
EEGDM Uses Latent Diffusion to Capture Global EEG Patterns
21h ago
0.24
167
Position Bias in Large Audio-Language Models Causes 24% Performance Fluctuations
21h ago
0.32
168
Arguments Against Generative AI's Impact on Startup Creation
21h ago
0.15
169
CanaryTrace Protects RAG Datasets via Watermarked Canaries
22h ago
0.32
170
LIMe Extension Increases Transformer Representation Capacity
22h ago
0.40
171
MUSE Platform for Multimodal Safety Evaluation of LLMs
22h ago
0.36
172
RSPO Framework for Regularized Self-Play Alignment
22h ago
0.39
173
AutoSciRub Framework Automates Scientific Research Agent Evaluation
22h ago
0.62
174
Scaling Reasoning Models via Verifiable Rewards and Experience
22h ago
0.84
175
MNIST-PRO Benchmark Tests Agentic Perception in Partial Observability
22h ago
0.48
176
Matrix-Game 3.5 Enhances Real-Time Interactive World Models
22h ago
0.69
177
NavMCP Framework Couples VLM Reasoning with NFM Execution
22h ago
0.76
178
MTPaperBananaBench Benchmarks Multi-Turn Scientific Diagram Refinement
22h ago
0.42
179
Cross-Lingual Transfer of Function Vectors for Emotion Detection
22h ago
0.36
180
BLARM Animates 3D Objects from Video via Motion Primitives
22h ago
0.62
181
CAST Improves Reliability of Long-Horizon Tool-Calling Agents
22h ago
0.69
182
CogEvol Generates Structured Learning Artifacts in Single Pass
22h ago
0.76
183
Analysis of On-Policy Distillation Noise and Student Convergence
22h ago
0.59
184
PaperGym Framework Automates Research Plan Generation
22h ago
0.46
185
GenFirst Optimizes End-to-End Latent Generative Modeling
22h ago
0.53
186
Lucida Enables Composable Real-to-Sim Scene Modeling
22h ago
0.58
187
Concept-Targeted Attribution for Interpreting Linear Probes
22h ago
0.24
188
Sequential vs. Parallel Test-Time Scaling in Machine Translation
22h ago
0.20
189
Survival Models for Web-Scale E-Commerce Repurchase Prediction
22h ago
0.18
190
Speculative Probing for Efficient LLM Monitoring
22h ago
0.34
191
Reference-Free Forced Alignment Evaluation via SSL Representations
22h ago
0.20
192
MCP Protocol Status and Stateless Specification Update
22h ago
0.36
193
CBHA* Algorithm for Constrained Spatial Planning via Heuristic Selection
23h ago
0.18
194
COVER Method for Identifiable Evaluation of Multi-Agent Coalition Routing
23h ago
0.18
195
Quality-Aware Framework for Medical Question Answering via Clinical Guidelines
23h ago
0.24
196
Offline Model-Based RL for Sequential Incentive Allocation in Advertising
23h ago
0.18
197
ContextPilot Framework for Proactive Agentic Context Management
23h ago
0.24
198
Ollama Transitions to Per-Token Pricing for Pro and Team Plans
23h ago
0.28
199
Using Markdown UI Kits to Improve LLM Generative Design Results
23h ago
0.28
200
GOD Control Room Enables Real-Time Intervention in Agent Societies
23h ago
0.31
← prev
page 4 / 5
next →