10 citations · 26 across the 22 of their papers we have counts for
22 papers
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…
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…
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…
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen +6
Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, maki…
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…
Data Diversification Methods In Alignment Enhance Math Performance In LLMs
Berkan Dokmeci, Qingyang Wu, Ben Athiwaratkun +3
While recent advances in preference learning have enhanced alignment in human feedback, mathematical reasoning remains a persistent challenge. We investigate how data diversificati…
Disentangling Reasoning and Knowledge in Medical Large Language Models
Rahul Thapa, Qingyang Wu, Kevin Wu +11
Medical reasoning in large language models (LLMs) aims to emulate clinicians' diagnostic thinking, but current benchmarks such as MedQA-USMLE, MedMCQA, and PubMedQA often mix reaso…
How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
Rahul Thapa, Andrew Li, Qingyang Wu +8
Publicly available biomedical videos, such as those on YouTube, serve as valuable educational resources for medical students. Unlike standard machine learning datasets, these video…
Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
Junlin Wang, Roy Xie, Shang Zhu +6
Building helpful and harmless large language models (LLMs) requires effective model alignment approach based on human instructions and feedback, which necessitates high-quality hum…
Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals
Junlin Wang, Shang Zhu, Jon Saad-Falcon +7
There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. While br…
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.…
Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
Rahul Thapa, Kezhen Chen, Ian Covert +4
Recent advances in vision-language models (VLMs) have demonstrated the advantages of processing images at higher resolutions and utilizing multi-crop features to preserve native re…
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…