126 citations · 388 across the 24 of their papers we have counts for
24 papers
WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
Xinlin Wang, Yujiao Xiang, Yuheng Zhou +11
Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent feature prediction. However, V-JEPA…
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
Wenlong Deng, Jiaji Huang, Kaan Ozkara +4
Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinfor…
EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
Zichen Wen, Boxue Yang, Junlong Ke +5
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most vide…
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
Minqing Huang, Yujiao Xiang, Zihan Liang +8
Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle to provide plannin…
Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
Shihao Ji, Zihui Song, Jiajie Huang
Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the Transformer's Softmax function, which creates "Artif…
AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
Peize He, Zichen Wen, Yubo Wang +13
Processing long-form audio is a major challenge for Large Audio Language models (LALMs). These models struggle with the quadratic cost of attention () and with modeling lon…
Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs
Hongyi Liu, Jiaji Huang, Zhen Jia +2
Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding…
ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
Hongyi Liu, Rajarshi Saha, Zhen Jia +5
Large Language Models (LLMs) have demonstrated exceptional performance in natural language processing tasks, yet their massive size makes serving them inefficient and costly. Semi-…
Inference Optimization of Foundation Models on AI Accelerators
Youngsuk Park, Kailash Budhathoki, Liangfu Chen +7
Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry an…
Data-Driven Adaptive Simultaneous Machine Translation
Guangxu Xun, Mingbo Ma, Yuchen Bian +7
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. H…
Exploiting a Zoo of Checkpoints for Unseen Tasks
Jiaji Huang, Qiang Qiu, Kenneth Church
There are so many models in the literature that it is difficult for practitioners to decide which combinations are likely to be effective for a new task. This paper attempts to add…
Better than BERT but Worse than Baseline
Boxiang Liu, Jiaji Huang, Xingyu Cai +1
This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition Identification (ADI) task. ADI inputs a text and outputs short forms (abbreviations/acronyms) and long forms…
DiffWave: A Versatile Diffusion Model for Audio Synthesis
Zhifeng Kong, Wei Ping, Jiaji Huang +2
In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts th…
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
Sherif Abdelkarim, Aniket Agarwal, Panos Achlioptas +5
Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale s…
Language Modeling at Scale
Mostofa Patwary, Milind Chabbi, Heewoo Jun +3
We show how Zipf's Law can be used to scale up language modeling (LM) to take advantage of more training data and more GPUs. LM plays a key role in many important natural language…
Large Margin Neural Language Model
Jiaji Huang, Yi Li, Wei Ping +1
We propose a large margin criterion for training neural language models. Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences.…
Topic Compositional Neural Language Model
Wenlin Wang, Zhe Gan, Wenqi Wang +5
We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering struc…
LDMNet: Low Dimensional Manifold Regularized Neural Networks
Wei Zhu, Qiang Qiu, Jiaji Huang +3
Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers f…
Reducing Bias in Production Speech Models
Eric Battenberg, Rewon Child, Adam Coates +13
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition. However, the causality and…
Active Learning for Speech Recognition: the Power of Gradients
Jiaji Huang, Rewon Child, Vinay Rao +3
In training speech recognition systems, labeling audio clips can be expensive, and not all data is equally valuable. Active learning aims to label only the most informative samples…
GraphConnect: A Regularization Framework for Neural Networks
Jiaji Huang, Qiang Qiu, Robert Calderbank +1
Deep neural networks have proved very successful in domains where large training sets are available, but when the number of training samples is small, their performance suffers fro…
Geometry-aware Deep Transform
Jiaji Huang, Qiang Qiu, Robert Calderbank +1
Many recent efforts have been devoted to designing sophisticated deep learning structures, obtaining revolutionary results on benchmark datasets. The success of these deep learning…
The Role of Principal Angles in Subspace Classification
Jiaji Huang, Qiang Qiu, Robert Calderbank
Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misc…
Changepoint detection for high-dimensional time series with missing data
Yao Xie, Jiaji Huang, Rebecca Willett
This paper describes a novel approach to change-point detection when the observed high-dimensional data may have missing elements. The performance of classical methods for change-p…