GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published 26 days ago • 218
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Paper • 2602.02472 • Published about 21 hours ago • 9
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published 4 days ago • 53
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text Paper • 2601.22975 • Published 4 days ago • 64
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone Paper • 2512.22615 • Published Dec 27, 2025 • 48
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation Paper • 2512.17495 • Published Dec 19, 2025 • 20
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation Paper • 2512.17495 • Published Dec 19, 2025 • 20 • 3
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation Paper • 2512.17495 • Published Dec 19, 2025 • 20
GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation Paper • 2512.17495 • Published Dec 19, 2025 • 20
Baichuan-M2: Scaling Medical Capability with Large Verifier System Paper • 2509.02208 • Published Sep 2, 2025 • 43