Article
What We Learned by Reproducing 2,200 papers from ICML
abidlabs
• • 74
free-bit
free-bit
AI & ML interests
None yet
Recent Activity
upvoted an article about 12 hours ago
What We Learned by Reproducing 2,200 papers from ICML upvoted an article about 12 hours ago
State of Open Models: Summer 2026 Observations upvoted an article about 12 hours ago
GGML and llama.cpp join HF to ensure the long-term progress of Local AIOrganizations
None yet
upvoted 3
articles about 12 hours ago
Article
State of Open Models: Summer 2026 Observations
- +1
AdinaY, multimodalart, irenesolaiman
• • 108 Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
ggerganov, ngxson, allozaur, lysandre, victor, julien-c
• • 510 upvoted 3
papers about 18 hours ago
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
Paper • 2608.13546 • Published • 123
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
Paper • 2608.14290 • Published • 31
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
Paper • 2608.14391 • Published • 258
upvoted 8
papers 4 days ago
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
Paper • 2608.11745 • Published • 22
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Paper • 2608.13552 • Published • 43
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Paper • 2608.13560 • Published • 47
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
Paper • 2608.12743 • Published • 42
Intern-S2-Preview: Scientific Agentic Foundation Model
Paper • 2608.13505 • Published • 58
DarwinX: Evolving Agent Harnesses Through Natural Selection
Paper • 2608.07545 • Published • 86
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
Paper • 2608.13489 • Published • 93
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Paper • 2608.06867 • Published • 103
upvoted 6
papers 5 days ago
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
Paper • 2608.08814 • Published • 10
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
Paper • 2608.11562 • Published • 9
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Paper • 2608.12307 • Published • 110
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Paper • 2608.11924 • Published • 280
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
Paper • 2608.08160 • Published • 27
StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization
Paper • 2608.12314 • Published • 25