…Yao Du , , Abstract A distribution-aware reinforcement learning framework improves multimodal large language models' numerical regression performance on long-tailed distributions through batch-level comparison-based supervision. AI-generated summary Multimodal large…
…On 170M-parameter language modeling , the shaped student at 8 steps achieves 32% lower perplexity than the 1,024-step teacher while being 128x faster, with gains consistent across source distributions and…
…Across Qwen3 0.6B--14B on domain-continual and capability-continual settings, GCWM consistently outperforms data-free baselines, improving retention and final performance without replay data. These results identify geometry conflict as…
…An Efficient Action-Centered World--Action Model (2026) Toward Physically Consistent Driving Video World Models under Challenging Trajectories (2026) EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action…
…Yuanyi Wang , Yanggan Gu , , , , , , , Abstract Empirical scaling laws for language model merging reveal power-law relationships between model size, expert count, and cross-entropy performance, enabling predictive planning for optimal model composition…
…The final dataset consists of 220k problems with verified reasoning traces, making it a valuable resource for training reasoning models I think the size should be 248k? otherwise, it seems like the…
…I ended up chasing /skills, /tmp/skills, .fast-agent/skills, .claude/skills, absolute paths… nothing was consistently accepted across runs. Model selection confusion / fast-agent flag collision -m means something else in…
…Definitely more consistency and token efficiency than Qwen. appreciate that your efforts on it. This kind of release notes are really useful, thank you Appreciate the great intro! Thank you! On the…