5 citations · 8 across the 18 of their papers we have counts for
21 papers
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Ruiyi Ding, Jie Li, Kang He +4
Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits. Such formats u…
AgenticGen: Reward-Guided Agentic Video Generation for Advertising
Xingyuan Bu, Chengru Song, Hao Zhou +9
Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video…
Beyond Attention Masks: Instruction Anchoring for Efficient In-Context Diffusion Generation
Yangshuai Liu, Zheming Li, Jiaao Li +4
In-context diffusion transformers concatenate instruction, target, and reference tokens into a single sequence for joint attention. Reference-side computation must therefore be rep…
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
Jie Li, Chenxin Jia, Jinliang Shen +5
In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts (METRO), assumin…
Latent Reward Registers for Diffusion Preference Alignment
Yuanshen Guan, Zipeng Feng, Chengru Song +2
Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, which creates a severe temporal credit-assignm…
X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion
Jianwen Xian, Zhiyuan Xu, Yuchen Li +9
Fine-grained, device-initiated communication allows fused GPU kernels to issue remote stores directly from their compute pipelines, a pattern increasingly used in expert parallelis…
JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models
Ruiyi Ding, Jie Li, He Kang +3
Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language m…
HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation
Jinliang Shen, Lianghao Su, Zheming Li +4
Autoregressive (AR) video diffusion models have become a promising paradigm for long and streaming video synthesis, but the continuously growing Key-Value (KV) cache makes attentio…
ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers
Ruiliang Zhou, Xuecheng Wu, Kang He +6
While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing s…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
OneReason Technical Report
OneRec Team, Biao Yang, Boyang Ding +81
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. Howev…
Kwai Summary Attention Technical Report
Chenglong Chu, Guorui Zhou, Guowang Zhang +35
Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agen…
: Re-conceptualizing Distribution Matching as a Reward for Diffusion Distillation
Linqian Fan, Peiqin Sun, Tiancheng Wen +2
Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniqu…
PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching
Qianchao Zhu, Xucheng Ye, Yuliang Liu +2
Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical M…
Kwai Keye-VL Technical Report
Kwai Keye Team, Biao Yang, Bin Wen +57
While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities on static images, they often fall short in comprehending dynamic, information-dense short-form vi…
SlimPipe: Memory-Thrifty and Efficient Pipeline Parallelism for Long-Context LLM Training
Zhouyang Li, Yuliang Liu, Wei Zhang +4
Pipeline Parallelism (PP) serves as a crucial technique for training Large Language Models (LLMs), owing to its capability to alleviate memory pressure from model states with relat…
VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
Xinlong Chen, Yuanxing Zhang, Chongling Rao +7
The training of controllable text-to-video (T2V) models relies heavily on the alignment between videos and captions, yet little existing research connects video caption evaluation…
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs
Chenxi Sun, Hongzhi Zhang, Zijia Lin +8
Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequen…
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Yang Jin, Zhicheng Sun, Kun Xu +9
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Co…
KwaiYiiMath: Technical Report
Jiayi Fu, Lei Lin, Xiaoyang Gao +18
Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on math…
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Yang Jin, Kun Xu, Liwei Chen +12
Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. How…