Karthik Iyer

kiyer97's activity

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

upvoted a paper about 15 hours ago

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

Paper • 2610.18067 • Published 4 days ago • 84

upvoted a paper 1 day ago

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published 8 days ago • 162

upvoted 2 papers 12 days ago

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

Paper • 2609.36651 • Published 18 days ago • 34

Rufus-Air: An Open LLM Post-Training Recipe

Paper • 2609.29421 • Published 23 days ago • 44

upvoted a paper 14 days ago

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published 21 days ago • 327

upvoted 2 papers 16 days ago

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Paper • 2609.28236 • Published 24 days ago • 39

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 22 days ago • 144

upvoted a paper 21 days ago

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Paper • 2609.26796 • Published 25 days ago • 37

upvoted 4 papers 22 days ago

Towards Full Pipeline FP8 Reinforcement Learning for LLMs

Paper • 2609.22870 • Published 28 days ago • 18

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Paper • 2609.13231 • Published Sep 2 • 19

VideoGen-Agent: Reinforcing Video Generation Agents

Paper • 2609.24997 • Published 26 days ago • 73

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

Paper • 2609.23377 • Published 27 days ago • 50

upvoted 6 papers 23 days ago

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 29 days ago • 138

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published Sep 4 • 119

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 606

MintAct: A Unified Visual Agent for Digital Environments

Paper • 2609.22083 • Published 29 days ago • 35

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

Paper • 2609.20886 • Published about 1 month ago • 30

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

Paper • 2609.21788 • Published 29 days ago • 13

upvoted 2 papers 24 days ago

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published 30 days ago • 41

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 30 days ago • 45