Aamer Mihaysi

O96a's activity

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

commented a paper about 4 hours ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 1 day ago • 34 •

2

commented a paper 1 day ago

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

Paper • 2607.07702 • Published 10 days ago • 7 •

3

commented a paper 2 days ago

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published 5 days ago • 12 •

4

commented a paper 3 days ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published 10 days ago • 125 •

3

commented a paper 4 days ago

KronQ: LLM Quantization via Kronecker-Factored Hessian

Paper • 2607.07964 • Published 10 days ago • 29 •

4

commented a paper 5 days ago

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

Paper • 2607.08716 • Published 9 days ago • 14 •

6

commented a paper 6 days ago

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published 16 days ago • 54 •

3

commented a paper 7 days ago

A Quantized Native Runtime for On-Device Semantic Audio Generation

Paper • 2607.08526 • Published 9 days ago • 4 •

4

commented a paper 8 days ago

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

Paper • 2607.01232 • Published 16 days ago • 6 •

3

commented a paper 9 days ago

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

Paper • 2607.05465 • Published 12 days ago • 12 •

3

commented a paper 10 days ago

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

Paper • 2607.05061 • Published 12 days ago • 23 •

3

commented a paper 11 days ago

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

Paper • 2607.01804 • Published 16 days ago • 31 •

4

commented a paper 13 days ago

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 17 days ago • 20 •

3

commented a paper 14 days ago

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

Paper • 2607.02255 • Published 16 days ago • 64 •

3

commented a paper 15 days ago

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

Paper • 2607.00466 • Published 17 days ago • 32 •

3

commented a paper 16 days ago

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

Paper • 2606.23127 • Published 26 days ago • 25 •

3

commented a paper 17 days ago

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

Paper • 2606.28733 • Published 21 days ago • 148 •

9

commented a paper 18 days ago

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

Paper • 2511.07397 • Published 17 days ago • 12 •

3

commented a paper 19 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 23 days ago • 4 •

3

commented a paper 20 days ago

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

Paper • 2606.26027 • Published 24 days ago • 18 •

3