3 citations · 12 across the 17 of their papers we have counts for
21 papers
ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor
Yixiao Wang, Ting Jiang, Zishan Shao +6
Denoising generative models deliver high-fidelity generation but remain bottlenecked by inference latency due to the many iterative denoiser calls required during sampling. Trainin…
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
Hancheng Ye, Zhengqi Gao, Mingyuan Ma +8
Multi-agent large language model (LLM) systems are increasingly adopted for complex language processing tasks that require communication and coordination among agents. However, the…
IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
Ningyuan Yang, Guanliang Lyu, Mingchen Ma +7
The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Conte…
DPad: Efficient Diffusion Language Models with Suffix Dropout
Xinhua Chen, Sitao Huang, Cong Guo +5
Diffusion-based Large Language Models (dLLMs) parallelize text generation by framing decoding as a denoising process, but suffer from high computational overhead since they predict…
Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals
Qinsi Wang, Jinghan Ke, Hancheng Ye +6
Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform…
SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues
Martin Kuo, Jianyi Zhang, Aolin Ding +12
Malicious attackers can exploit large language models (LLMs) by engaging them in multi-turn dialogues to achieve harmful objectives, posing significant safety risks to society. To…
CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
Qinsi Wang, Hancheng Ye, Ming-Yu Chung +6
Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neur…
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
Yudong Liu, Jingwei Sun, Yueqian Lin +6
Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to red…
Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI
Jianyi Zhang
Recent years have witnessed the rapid progression of deep learning, pushing us closer to the realization of AGI (Artificial General Intelligence). Probabilistic modeling is critica…
Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility
Martin Kuo, Jingyang Zhang, Jianyi Zhang +9
With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although…
H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
Martin Kuo, Jianyi Zhang, Aolin Ding +6
Large Reasoning Models (LRMs) have recently extended their powerful reasoning capabilities to safety checks-using chain-of-thought reasoning to decide whether a request should be a…
SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
Yueqian Lin, Yuzhe Fu, Jingyang Zhang +5
We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models…
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren, Jianyi Zhang, Chun-Sung Ferng +3
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whet…
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian +3
Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Log…
CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation
Qinsi Wang, Saeed Vahidian, Hancheng Ye +3
Large language models (LLMs) with billions of parameters have sparked a new wave of exciting AI applications. However, their high computational costs and memory demands during infe…
Federated Large Language Models: Current Progress and Future Directions
Yuhang Yao, Jianyi Zhang, Junda Wu +11
Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy…
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
Jianyi Zhang, Hao Frank Yang, Ang Li +5
Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients. In light of the recent advances in multimodal…
ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models
Jianyi Zhang, Yufan Zhou, Jiuxiang Gu +5
Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often g…
Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models
Jingyang Zhang, Jingwei Sun, Eric Yeats +5
The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and t…
Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
Yuqi Jia, Saeed Vahidian, Jingwei Sun +4
Data heterogeneity presents significant challenges for federated learning (FL). Recently, dataset distillation techniques have been introduced, and performed at the client level, t…
DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration
Martin Kuo, Jianyi Zhang, Dongting Li +1
Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable p…