Aamer Mihaysi

O96a's activity

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

commented a paper about 3 hours ago

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Paper • 2607.01232 • Published 8 days ago • 3 •

2

commented a paper 1 day ago

CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration

Paper • 2607.05465 • Published 4 days ago • 9 •

2

commented a paper 2 days ago

KVpop -- Key-Value Cache Compression with Predictive Online Pruning

Paper • 2607.05061 • Published 4 days ago • 19 •

3

commented a paper 3 days ago

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

Paper • 2607.01804 • Published 8 days ago • 28 •

4

commented a paper 5 days ago

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 9 days ago • 19 •

3

commented a paper 6 days ago

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published 8 days ago • 60 •

3

commented a paper 7 days ago

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving

Paper • 2607.00466 • Published 9 days ago • 31 •

3

commented a paper 8 days ago

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation

Paper • 2606.23127 • Published 18 days ago • 24 •

3

commented a paper 9 days ago

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published 13 days ago • 146 •

9

commented a paper 10 days ago

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

Paper • 2511.07397 • Published 9 days ago • 12 •

3

commented a paper 11 days ago

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Paper • 2606.27288 • Published 15 days ago • 4 •

3

commented a paper 12 days ago

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

Paper • 2606.26027 • Published 16 days ago • 18 •

3

commented a paper 13 days ago

The Verification Horizon: No Silver Bullet for Coding Agent Rewards

Paper • 2606.26300 • Published 16 days ago • 49 •

4

commented a paper 14 days ago

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

Paper • 2606.25605 • Published 16 days ago • 3 •

3

commented a paper 15 days ago

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

Paper • 2606.24428 • Published 17 days ago • 52 •

3

commented a paper 16 days ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published 20 days ago • 24 •

13

updated a Space about 2 months ago

Build error

Agents

MMSkills Demo - Multimodal Skill Retrieval for Visual Agents

🤖

published a Space about 2 months ago

Build error

Agents

MMSkills Demo - Multimodal Skill Retrieval for Visual Agents

🤖

updated a Space about 2 months ago

Build error

Agents

MMSkills Demo - Multimodal Skill Retrieval for Visual Agents

🤖

published a Space about 2 months ago

Build error

Agents

MMSkills Demo - Multimodal Skill Retrieval for Visual Agents

🤖