222 citations · 457 across the 31 of their papers we have counts for
11 papers · 1 filter
Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model
Liming Lu, Xianzheng Ma, Wenkun He +14
Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approac…
Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs
Haozhan Tang, Hao Kang, Han Cai +2
Reliable FP8 attention remains a barrier to fully native 8-bit large language model training. We derive how forward-backward inconsistencies produce stale delta and empirically sho…
Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models
Yecheng Wu, Song Han, Han Cai
On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD su…
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
Haozhan Tang, Zerui Wang, Yuxian Gu +2
Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasonin…
ActionMap: Robot Policy Learning via Voxel Action Heatmap
Pei Yang, Hai Ci, Yanzhe Chen +3
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state int…
JetViT: Efficient High-Resolution Vision Transformer with Post-Training Attention Search
Dongyun Zou, Zhuoyang Zhang, Junyu Chen +8
We introduce JetViT, a novel family of hybrid-architecture Vision Transformer (ViT) models that match the accuracy of state-of-the-art full-attention vision foundation models while…
Hide to Guide: Learning via Semantic Masking
Ruitao Liu, Qinghao Hu, Alex Hu +6
Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but its effectiveness is often limi…
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
Yuchao Gu, Guian Fang, Yuxin Jiang +4
Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling step…
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Shuo Yang, Haocheng Xi, Yilong Zhao +10
-means has historically been positioned primarily as an offline processing primitive, typically used for dataset organization or embedding preprocessing rather than as a first-c…
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Haocheng Xi, Shuo Yang, Yilong Zhao +13
Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregre…
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Haocheng Xi, Charlie Ruan, Peiyuan Liao +7
Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computational…