3 citations · 6 across the 17 of their papers we have counts for
19 papers
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
Yu-Yang Qian, Junda Su, Lanxiang Hu +4
Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these…
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
Chenkai Xu, Yijie Jin, Jiajun Li +8
Diffusion Large Language Models (dLLMs) have demonstrated significant potential for high-speed inference. However, current confidence-driven decoding strategies are constrained by…
DEER: Draft with Diffusion, Verify with Autoregressive Models
Zicong Cheng, Guo-Wei Yang, Jia Li +3
Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Spe…
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
Lanxiang Hu, Siqi Kou, Yichao Fu +5
Multi-token generation has emerged as a promising paradigm for accelerating transformer-based large model inference. Recent efforts primarily explore diffusion Large Language Model…
Adaptive Discretization for Consistency Models
Jiayu Bai, Zhanbo Feng, Zhijie Deng +3
Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated…
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Xu Wang, Chenkai Xu, Yijie Jin +3
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a s…
Scaling Speculative Decoding with Lookahead Reasoning
Yichao Fu, Rui Ge, Zelei Shao +2
Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is…
Fast Quiet-STaR: Thinking Without Thought Tokens
Wei Huang, Yizhe Xiong, Xin Ye +4
Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains parti…
Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
Hangliang Ding, Dacheng Li, Runlong Su +4
Despite the promise of synthesizing high-fidelity videos, Diffusion Transformers (DiTs) with 3D full attention suffer from expensive inference due to the complexity of attention co…
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
Junkai Chen, Zhijie Deng, Kening Zheng +6
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forge…
Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
Zijun Chen, Wenbo Hu, Guande He +3
Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial…
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
Siqi Kou, Jiachun Jin, Zhihong Liu +6
We introduce Orthus, an autoregressive (AR) transformer that excels in generating images given textual prompts, answering questions based on visual inputs, and even crafting length…
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
Bokai Lin, Zihao Zeng, Zipeng Xiao +5
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) a…
In-context KV-Cache Eviction for LLMs via Attention-Gate
Zihao Zeng, Bokai Lin, Tianqi Hou +2
The KV-Cache technique has become the standard for the inference of large language models (LLMs). Yet, it is widely criticized that KV-Cache can become a bottleneck of the LLM infe…
SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
Kang You, Zekai Xu, Chen Nie +4
Spiking neural network (SNN) has attracted great attention due to its characteristic of high efficiency and accuracy. Currently, the ANN-to-SNN conversion methods can obtain ANN on…
TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput
Xiaoxuan Liu, Jongseok Park, Langxiang Hu +10
Large Language Model (LLM) serving systems batch concurrent user requests to achieve efficient serving. However, in real-world deployments, such inter-request parallelism from batc…
CLLMs: Consistency Large Language Models
Siqi Kou, Lanxiang Hu, Zhezhi He +2
Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it int…
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
Siqi Kou, Lei Gan, Dequan Wang +2
Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper samp…
Online Speculative Decoding
Xiaoxuan Liu, Lanxiang Hu, Peter Bailis +4
Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. Ho…