Asa Cross

asacross's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 19 hours ago

Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling

Paper • 2607.01642 • Published 6 days ago • 37

upvoted 2 papers 3 days ago

When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

Paper • 2606.20023 • Published 20 days ago • 5

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

Paper • 2511.07397 • Published 7 days ago • 12

upvoted a paper 5 days ago

Dockerless: Environment-Free Program Verifier for Coding Agents

Paper • 2606.28436 • Published 12 days ago • 108

upvoted a paper 6 days ago

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

Paper • 2606.30251 • Published 9 days ago • 21

upvoted 2 papers 8 days ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Paper • 2606.26027 • Published 14 days ago • 18

Discretizing Reward Models

Paper • 2606.21795 • Published 19 days ago • 17

upvoted 3 papers 9 days ago

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

Paper • 2606.25605 • Published 14 days ago • 3

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

Paper • 2606.24937 • Published 16 days ago • 18

Semantic Browsing: Controllable Diversity for Image Generation

Paper • 2606.23679 • Published 16 days ago • 20

upvoted a paper 11 days ago

EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies

Paper • 2606.20092 • Published 20 days ago • 6

upvoted a paper 12 days ago

MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management

Paper • 2606.19926 • Published 20 days ago • 42

upvoted a paper 13 days ago

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

Paper • 2606.23654 • Published 16 days ago • 79

upvoted a paper 14 days ago

GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents

Paper • 2606.18829 • Published 21 days ago • 18

upvoted 2 papers 15 days ago

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

Paper • 2606.19980 • Published 20 days ago • 15

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 21 days ago • 139

upvoted 2 papers 16 days ago

Guava: An Effective and Universal Harness for Embodied Manipulation

Paper • 2606.18363 • Published 22 days ago • 28

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

Paper • 2606.19236 • Published 21 days ago • 13

upvoted 2 papers 17 days ago

AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models

Paper • 2606.08952 • Published about 1 month ago • 4

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published 22 days ago • 209