10 citations · 32 across the 22 of their papers we have counts for
24 papers
On-Policy Residual Learning for Diffusion Language Models
Yifan Yu, Yuqing Jian, Jisen Li +9
Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions across denoising steps. Yet…
QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs
Weili Xu, Jisen Li, Yuqing Jian +8
Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive post-training quantization (PT…
Tail-Likelihood Reinforcement Learning
Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar +11
Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achieve the same mean reward whi…
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
Fengxiang Bie, Yuqing Jian, Yifan Yu +7
Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: drafters are typically trained against a narrow distribution for a single target m…
Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus
Zunhai Su, Bohan Sun, Xialie Zhuang +9
We present the first systematic study of massive activations (MAs) in layer-interleaved Hybrid linear attention large language models (HLA LLMs), examining their architectural orga…
Linear RNN Scaling Laws: When Longer Sequences Beat More Sequences
Ziyan Chen, Zhongzhu Zhou, Peilin Liu +2
Empirical scaling laws for autoregressive language models relate prediction loss to model size, data size, and optimization compute, but their theoretical origin is still poorly un…
Compute Allocation in Bilinear Contrastive Representation Learning via Scaling Laws
Ziyan Chen, Zhongzhu Zhou, Ding-Xuan Zhou
Efficient reasoning systems increasingly rely on large contrastive representation models for multimodal retrieval, grounding, and decision-making. However, under a limited compute…
Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation
Zhongzhu Zhou, Qingyang Wu, Junxiong Wang +4
Hybrid linear attention models offer an appealing path to faster long-context inference: they reduce the quadratic cost and KV-cache burden of full softmax attention while retainin…
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
Zhongzhu Zhou, Donglin Zhuang, Jisen Li +4
INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations such as Hadamard transforms r…
Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression
Ziyan Chen, Zhongzhu Zhou, Ding-Xuan Zhou
Mini-batching is central to large-scale optimization, yet its role in statistical scaling laws remains limited. We study one-pass and multi-pass batch SGD for sketched linear regre…
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…
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…
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li +14
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
Zhenyu Zhang, Xiaoxia Wu, Zhongzhu Zhou +7
Large Language Models (LLMs) often rely on long chain-of-thought (CoT) reasoning to solve complex tasks. While effective, these trajectories are frequently inefficient, leading to…
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia, Xiaoxia Wu, Jisen Li +12
The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We cl…
Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient
Zhongzhu Zhou, Yibo Yang, Ziyan Chen +7
Policy gradient (PG) methods in reinforcement learning frequently utilize deep neural networks (DNNs) to learn a shared backbone of feature representations used to compute likeliho…
Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping
Muru Zhang, Mayank Mishra, Zhongzhu Zhou +7
Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are us…
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
Yibo Yang, Xiaojie Li, Zhongzhu Zhou +4
Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain.…
FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
Haojun Xia, Zhen Zheng, Xiaoxia Wu +10
Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing…
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang +89
In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scient…
Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
Haojun Xia, Zhen Zheng, Yuchao Li +6
With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive com…
RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
Fengxiang Bie, Yibo Yang, Zhongzhu Zhou +10
Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions. Text-to-image generation us…
DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales
Zhewei Yao, Reza Yazdani Aminabadi, Olatunji Ruwase +16
ChatGPT-like models have revolutionized various applications in artificial intelligence, from summarization and coding to translation, matching or even surpassing human performance…