activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models

Minseo Kim, Coleman Hooper, Aditya Tomar +5

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generati…

cs.LG2025

Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

Qinsi Wang, Jinghan Ke, Hancheng Ye +6

Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform…

cs.LG2025

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity

Samir Khaki, Xiuyu Li, Junxian Guo +7

Fine-tuning LLMs is both computationally and memory-intensive. While parameter-efficient fine-tuning methods, such as QLoRA and DoRA, reduce the number of trainable parameters and…

cs.LG2025

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

Qinsi Wang, Jinghan Ke, Masayoshi Tomizuka +3

We provide a new LLM-compression solution via SVD, unlocking new possibilities for LLM compression beyond quantization and pruning. We point out that the optimal use of SVD lies in…