849 citations · 2.4k across the 172 of their papers we have counts for
178 papers
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
Guannan Lai, Haoran Hu, Long Chen +2
Existing LLM routing methods often construct supervision from a single sampled response for each query--model pair. Because LLM generation is stochastic, however, such an observati…
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
Guannan Lai, Da-Wei Zhou, Zhenguo Li +1
Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods…
DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
Zirui Wu, Lin Zheng, Zhihui Xie +8
Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, th…
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
Yao Teng, Fuyun Wang, Xian Liu +7
As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requir…
Masked Diffusion Models as Energy Minimization
Sitong Chen, Shen Nie, Jiacheng Sun +4
We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specificall…
Dream-Coder 7B: An Open Diffusion Language Model for Code
Zhihui Xie, Jiacheng Ye, Lin Zheng +8
We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoreg…
Dream 7B: Diffusion Large Language Models
Jiacheng Ye, Zhihui Xie, Lin Zheng +5
We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete…
Mathesis: Towards Formal Theorem Proving from Natural Languages
Yu Xuejun, Jianyuan Zhong, Zijin Feng +17
Recent advances in large language models show strong promise for formal reasoning. However, most LLM-based theorem provers have long been constrained by the need for expert-written…
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
Shuchen Xue, Tianyu Xie, Tianyang Hu +5
Efficiently scaling Large Language Models (LLMs) necessitates exploring alternatives to dominant autoregressive (AR) methods, with Masked Diffusion Models (MDMs) emerging as candid…
Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
Yunhao Gou, Kai Chen, Zhili Liu +5
Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, h…
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Jin Wang, Yao Lai, Aoxue Li +6
The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation with…
Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling
Tianyu Xie, Shuchen Xue, Zijin Feng +4
Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality…
Adding Additional Control to One-Step Diffusion with Joint Distribution Matching
Yihong Luo, Tianyang Hu, Yifan Song +3
While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as nove…
Empowering Sparse-Input Neural Radiance Fields with Dual-Level Semantic Guidance from Dense Novel Views
Yingji Zhong, Kaichen Zhou, Zhihao Li +3
Neural Radiance Fields (NeRF) have shown remarkable capabilities for photorealistic novel view synthesis. One major deficiency of NeRF is that dense inputs are typically required,…
Implicit Search via Discrete Diffusion: A Study on Chess
Jiacheng Ye, Zhenyu Wu, Jiahui Gao +4
In the post-AlphaGo era, there has been a renewed interest in search techniques such as Monte Carlo Tree Search (MCTS), particularly in their application to Large Language Models (…
Self-Adjust Softmax
Chuanyang Zheng, Yihang Gao, Guoxuan Chen +7
The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other altern…
Improved Diffusion-based Generative Model with Better Adversarial Robustness
Zekun Wang, Mingyang Yi, Shuchen Xue +4
Diffusion Probabilistic Models (DPMs) have achieved significant success in generative tasks. However, their training and sampling processes suffer from the issue of distribution mi…
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
Yunhao Gou, Hansi Yang, Zhili Liu +8
Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), yet its effectiveness is often compromised by corrupted datasets with issues such as hallu…
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Yixin Ou, Yunzhi Yao, Ningyu Zhang +5
Despite exceptional capabilities in knowledge-intensive tasks, Large Language Models (LLMs) face a critical gap in understanding how they internalize new knowledge, particularly ho…
ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis
Haoxiong Liu, Jiacheng Sun, Zhenguo Li +1
The synergy between deep learning models and traditional automation tools, such as built-in tactics of the proof assistant and off-the-shelf automated theorem provers, plays a cruc…
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Jiahao Wang, Ning Kang, Lewei Yao +12
In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Throu…
Efficient Multi-modal Large Language Models via Visual Token Grouping
Minbin Huang, Runhui Huang, Han Shi +6
The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a…
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
Guoxuan Chen, Han Shi, Jiawei Li +7
Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable chall…
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
Kaican Li, Weiyan Xie, Yongxiang Huang +5
Fine-tuning foundation models often compromises their robustness to distribution shifts. To remedy this, most robust fine-tuning methods aim to preserve the pre-trained features. H…