The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
Paper • 2610.36077 • Published • 48
afdfjl
jojf23423424
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents upvoted a paper 12 days ago
VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents upvoted a paper 13 days ago
ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local NavigationOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted a paper 12 days ago
upvoted a paper 13 days ago
upvoted a paper 22 days ago
upvoted a paper 28 days ago
upvoted 7
papers about 1 month ago
Video Generation Models: A Survey of Post-Training and Alignment
Paper • 2610.00812 • Published • 23
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
Paper • 2609.39027 • Published • 21
Agent Priors-guided Policy Learning
Paper • 2609.35690 • Published • 55
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement
Paper • 2609.39045 • Published • 48
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Paper • 2609.33439 • Published • 120
CoWindow Attention: Full Causal Coverage Is a Collective Property
Paper • 2609.32704 • Published • 23
MassAlloc Attention: Let Attention Allocate Its Own Compute
Paper • 2609.32712 • Published • 30
upvoted 2
papers about 2 months ago
upvoted 4
papers 2 months ago
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
Paper • 2609.00638 • Published • 42
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Paper • 2609.01343 • Published • 65
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Paper • 2608.27456 • Published • 55
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Paper • 2608.17253 • Published • 49
upvoted 2
papers 3 months ago