GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Paper • 2604.14258 • Published • 23
Попов Тимофей
benjaminmitchel
AI & ML interests
None yet
Recent Activity
liked a dataset 6 days ago
xjh111/nanoresearch-20topics liked a model 10 days ago
meta-llama/Meta-Llama-3-8B-Instruct liked a model 16 days ago
Tangc03/UniCharacterOrganizations
None yet
upvoted a paper 23 days ago
upvoted 5
papers about 1 month ago
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
Paper • 2604.07429 • Published • 121
PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models
Paper • 2604.08340 • Published • 8
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Paper • 2604.03922 • Published • 53
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Paper • 2603.26164 • Published • 364
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
Paper • 2604.01618 • Published • 15
upvoted 3
papers about 2 months ago
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Paper • 2603.24414 • Published • 183
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
Paper • 2603.28032 • Published • 342
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 371