EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
Paper • 2606.20092 • Published • 1
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 6 hours ago
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies upvoted a paper about 6 hours ago
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning upvoted a paper about 14 hours ago
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure InteractionOrganizations
None yet
upvoted 2
papers about 6 hours ago
upvoted a paper about 14 hours ago
upvoted 4
papers about 16 hours ago
OpenThoughts-Agent: Data Recipes for Agentic Models
Paper • 2606.24855 • Published • 16
Qwen-AgentWorld: Language World Models for General Agents
Paper • 2606.24597 • Published • 79
MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
Paper • 2606.19930 • Published • 34
MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management
Paper • 2606.19926 • Published • 33
upvoted 8
papers about 18 hours ago
Go-with-the-Track: Video Compositing and Motion Control with Point Tracking
Paper • 2606.20891 • Published • 2
Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
Paper • 2606.23688 • Published • 2
MeshFlow: Mesh Generation with Equivariant Flow Matching
Paper • 2606.23489 • Published • 2
Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation
Paper • 2606.23514 • Published • 3
Vera: A Layered Diffusion Model for Content-Preserving Video Editing
Paper • 2606.23610 • Published • 6
Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding
Paper • 2606.21906 • Published • 20
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Paper • 2606.23654 • Published • 71
PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
Paper • 2606.22388 • Published • 85
upvoted 5
papers 1 day ago
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Paper • 2606.22883 • Published • 31
Tmax: A simple recipe for terminal agents
Paper • 2606.23321 • Published • 10
Unlimited OCR Works
Paper • 2606.23050 • Published • 23
Causal Discovery in the Era of Agents
Paper • 2606.23608 • Published • 6
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
Paper • 2606.20002 • Published • 8