M Saad Salman

MSS444's activity

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

upvoted 4 papers 4 days ago

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

Paper • 2610.09832 • Published 5 days ago • 8

Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads

Paper • 2610.05034 • Published 8 days ago • 19

Recurrent Looped Transformer

Paper • 2610.07591 • Published 6 days ago • 28

Questioning the Questions: Sustaining Self-Evolution in Reasoning Models

Paper • 2610.04299 • Published 9 days ago • 70

upvoted 2 papers 6 days ago

Base Models Can Reason By Taking a Cue From Training Data

Paper • 2610.06851 • Published 7 days ago • 25

PaLoRA: Paced Low-Rank Adaptation for Continual Learning

Paper • 2610.04226 • Published 9 days ago • 10

upvoted 3 papers 7 days ago

CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning

Paper • 2609.36820 • Published 13 days ago • 41

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 11 days ago • 46

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Paper • 2609.36585 • Published 13 days ago • 71

upvoted a paper 10 days ago

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Paper • 2609.40097 • Published 12 days ago • 50

upvoted 8 papers 11 days ago

Jev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration

Paper • 2609.35342 • Published 14 days ago • 8

Language Models Are "Insecure" Reporters

Paper • 2609.36139 • Published 14 days ago • 17

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published 13 days ago • 39

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published 13 days ago • 100

Omni-IO Skills: Harnessing Your Agent Omni-Native

Paper • 2609.31847 • Published 17 days ago • 451

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 15 days ago • 675

SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

Paper • 2609.38822 • Published 12 days ago • 7

AIM: Agentic Idea Management for Automated Research

Paper • 2609.38445 • Published 13 days ago • 53

upvoted 2 papers 14 days ago

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

Paper • 2609.27334 • Published 19 days ago • 56

PUBG Ally: A Conversational Embodied Agent as an AI Teammate

Paper • 2609.29837 • Published 18 days ago • 25