8 papers
Latent Thought Flow: Efficient Latent Reasoning in Large Language Models
Xiandong Zou, Jing Huang, Jianshu Li +1
Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decod…
Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance
Xiandong Zou, Jianshu Li, Jing Huang +1
Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves…
IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
Xiandong Zou, Jia Li, Xiaotong Yuan +1
Normalization is fundamental to deep learning, but existing approaches such as BatchNorm, LayerNorm, and RMSNorm are variance-centric by enforcing zero mean and unit variance, stab…
Benchmarking Gaslighting Attacks Against Speech Large Language Models
Jinyang Wu, Bin Zhu, Xiandong Zou +3
As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input beco…
DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision
Xiandong Zou, Ruihao Xia, Hongsong Wang +1
While text-to-3D generation has attracted growing interest, existing methods often struggle to produce 3D assets that align well with human preferences. Current preference alignmen…
Cached Multi-Lora Composition for Multi-Concept Image Generation
Xiandong Zou, Mingzhu Shen, Christos-Savvas Bouganis +1
Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and style…
HPS: Hard Preference Sampling for Human Preference Alignment
Xiandong Zou, Wanyu Lin, Yuchen Li +1
Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett…
Will More Expressive Graph Neural Networks do Better on Generative Tasks?
Xiandong Zou, Xiangyu Zhao, Pietro Liò +1
Graph generation poses a significant challenge as it involves predicting a complete graph with multiple nodes and edges based on simply a given label. This task also carries fundam…