Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published 8 days ago • 72
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 10 days ago • 165
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 13 days ago • 203
sashaboguraev/pythia-1b-ppt-control_shuffle_dyck_steps250_1b-seed208 Text Generation • 1B • Updated Jun 4 • 3 • 1
DCAgent3/bfcl_parity_a3_rl_laion_nemotron_gym_math_advanced_calculations_v3_60_8B_202606a55b0e3b Viewer • Updated Jun 3 • 368 • 20 • 1
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published Jun 1 • 241
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Paper • 2605.30621 • Published May 28 • 23
quiet-storm/univla-policy-lerobot-fixedstats-fps-banpot-eu5-fps5-step10000-wrist-decoder-residual Updated May 21 • 5 • 1
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196