1 citations · 2 across the 24 of their papers we have counts for
12 papers · 1 filter
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Haocheng Xi, Yiming Xie, Hexu Zhao +8
Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appeal…
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
Shuo Yang, Xiaoze Fan, Melissa Pan +8
Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system th…
REAR: Test-time Preference Realignment through Reward Decomposition
Fuxiang Zhang, Pengcheng Wang, Chenran Li +6
Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often r…
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
Dennis Menn, Yuedong Yang, Bokun Wang +6
Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting…
SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
Jinda Jia, Jisen Li, Zhongzhu Zhou +8
KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent wor…
Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias
Zhiyuan Xu, Jiuming Liu, Yuxin Chen +3
We present SparseGen, a novel framework for efficient image-to-3D generation, which exhibits low input-view bias while being significantly faster. Unlike traditional approaches tha…
LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
Haocheng Xi, Harman Singh, Yuezhou Hu +9
Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still rem…
Introspective Diffusion Language Models
Yifan Yu, Yuqing Jian, Junxiong Wang +12
Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR mo…
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou +16
We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, whi…
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…
Residual Context Diffusion Language Models
Yuezhou Hu, Harman Singh, Monishwaran Maheswaran +10
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. Howeve…