GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Paper • 2606.28187 • Published • 12
Finn Reyes
finnreyes
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems upvoted a paper about 8 hours ago
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering upvoted a paper about 8 hours ago
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic ReasoningOrganizations
None yet
upvoted 4
papers about 8 hours ago
ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering
Paper • 2606.27974 • Published • 11
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Paper • 2606.22873 • Published • 13
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Paper • 2606.28128 • Published • 48
upvoted 4
papers 1 day ago
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Paper • 2606.26300 • Published • 46
In-Context World Modeling for Robotic Control
Paper • 2606.26025 • Published • 61
Fast LeWorldModel
Paper • 2606.26217 • Published • 26
DanceOPD: On-Policy Generative Field Distillation
Paper • 2606.27377 • Published • 80
upvoted 9
papers 3 days ago
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
Paper • 2606.20092 • Published • 6
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
Paper • 2606.24526 • Published • 4
ChartWalker: Benchmarking the Cross-Chart RAG Task
Paper • 2606.23997 • Published • 3
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
Paper • 2606.20027 • Published • 3
Qwen-AgentWorld: Language World Models for General Agents
Paper • 2606.24597 • Published • 144
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Paper • 2606.20521 • Published • 14
OpenRath: Session-Centered Runtime State for Agent Systems
Paper • 2606.19409 • Published • 77
OpenThoughts-Agent: Data Recipes for Agentic Models
Paper • 2606.24855 • Published • 46
Semantic Browsing: Controllable Diversity for Image Generation
Paper • 2606.23679 • Published • 20
upvoted 3
papers 5 days ago
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Paper • 2606.24530 • Published • 62
DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis
Paper • 2604.13416 • Published • 33
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
Paper • 2606.24133 • Published • 11