Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training
Paper • 2606.11854 • Published • 3
Kye Gomez
kye
AI & ML interests
Neuroscience, Behavior Science, Anti-Matter, Anti-Gravity propulsion,
Recent Activity
upvoted a paper about 7 hours ago
Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training upvoted a paper about 7 hours ago
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning upvoted a paper about 7 hours ago
InternVideo3: Agentify Foundation Models with Multimodal Contextual ReasoningOrganizations
upvoted 7
papers about 7 hours ago
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Paper • 2606.11119 • Published • 15
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
Paper • 2606.12195 • Published • 17
On Subquadratic Architectures: From Applications to Principles
Paper • 2606.12364 • Published • 20
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
Paper • 2606.12403 • Published • 22
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 67
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Paper • 2606.12397 • Published • 74
upvoted 3
papers 1 day ago
Dynamic Linear Attention
Paper • 2606.10650 • Published • 3
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Paper • 2606.05304 • Published • 5
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 49
upvoted 8
papers 2 days ago
Agents' Last Exam
Paper • 2606.05405 • Published • 266
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Paper • 2606.07297 • Published • 108
Phase Marginalization for Patch-Grid Instability in Vision Transformers
Paper • 2606.08132 • Published • 3
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
Paper • 2606.07299 • Published • 6
Why Muon Outperforms Adam: A Curvature Perspective
Paper • 2606.04662 • Published • 8
End-to-End Context Compression at Scale
Paper • 2606.09659 • Published • 22
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Paper • 2606.06087 • Published • 59
Latent Spatial Memory for Video World Models
Paper • 2606.09828 • Published • 62
upvoted 2
papers 3 days ago