1 citations · 6 across the 24 of their papers we have counts for
24 papers
Training Language Models to Cooperate with Inference-Time Controllers
Moumita Choudhury, Vanshaj Khattar, Jing Liu +4
Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reasoning. Existing post-training…
Beyond Heavy Log Curation: Perplexity-Based APT Detection via Unsupervised, Context-Augmented Language Models
Shoya Otsu, Kei Suzuki, Toshiaki Koike-Akino +2
Advanced Persistent Threats (APTs) remain difficult to detect because only a small fraction of events in large-scale logs are attack-related, and investigation is expensive and har…
ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
Haodi Hu, Chung-Ta Huang, Jing Liu +4
Vision-language-action (VLA) policies provide strong priors for language-conditioned manipulation, but remain brittle in off-nominal states requiring targeted recovery. We propose…
EinSort: Sorting is All We Need for Tensorizing LLM
Toshiaki Koike-Akino, Jing Liu, Ye Wang
Tensor networks provide efficient representations for compressing large neural networks. By carefully designing shapes and topologies, they can significantly reduce memory and comp…
Mastering the Minority: An Uncertainty-guided Multi-Expert Framework for Challenging-tailed Sequence Learning
Ye Wang, Zixuan Wu, Lifeng Shen +4
Imbalanced data distribution remains a critical challenge in sequential learning, leading models to easily recognize frequent categories while failing to detect minority classes ad…
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4
Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test…
Directional Embedding Smoothing for Robust Vision Language Models
Ye Wang, Jing Liu, Toshiaki Koike-Akino
The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain vulnerable to jailbreaking attacks…
AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
Jing Liu, Toshiaki Koike-Akino, Ye Wang +2
To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this w…
TuneComp: Joint Fine-tuning and Compression for Large Foundation Models
Xiangyu Chen, Jing Liu, Ye Wang +4
To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model…
-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts
Toshiaki Koike-Akino, Jing Liu, Ye Wang
To tackle the huge computational demand of large foundation models, activation-aware compression techniques without retraining have been introduced. However, since these rely on ca…
LatentLLM: Attention-Aware Joint Tensor Compression
Toshiaki Koike-Akino, Xiangyu Chen, Jing Liu +4
Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new f…
Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in Product QA Agents
Ashley Lewis, Michael White, Jing Liu +3
The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To addres…
Smoothed Embeddings for Robust Language Models
Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis +4
Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful con…
Quantum Diffusion Models for Few-Shot Learning
Ruhan Wang, Ye Wang, Jing Liu +1
Modern quantum machine learning (QML) methods involve the variational optimization of parameterized quantum circuits on training datasets, followed by predictions on testing datase…
Exploring User-level Gradient Inversion with a Diffusion Prior
Zhuohang Li, Andrew Lowy, Jing Liu +4
We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private in…
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
Md Rafi Ur Rashid, Jing Liu, Toshiaki Koike-Akino +2
Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular communi…
Analyzing Inference Privacy Risks Through Gradients in Machine Learning
Zhuohang Li, Andrew Lowy, Jing Liu +4
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privac…
Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
Ryo Hase, Ye Wang, Toshiaki Koike-Akino +2
Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural…
Random Channel Ablation for Robust Hand Gesture Classification with Multimodal Biosignals
Keshav Bimbraw, Jing Liu, Ye Wang +1
Biosignal-based hand gesture classification is an important component of effective human-machine interaction. For multimodal biosignal sensing, the modalities often face data loss…
GPT Sonograpy: Hand Gesture Decoding from Forearm Ultrasound Images via VLM
Keshav Bimbraw, Ye Wang, Jing Liu +1
Large vision-language models (LVLMs), such as the Generative Pre-trained Transformer 4-omni (GPT-4o), are emerging multi-modal foundation models which have great potential as power…
Efficient Differentially Private Fine-Tuning of Diffusion Models
Jing Liu, Andrew Lowy, Toshiaki Koike-Akino +2
The recent developments of Diffusion Models (DMs) enable generation of astonishingly high-quality synthetic samples. Recent work showed that the synthetic samples generated by the…
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
Haomiao Ni, Bernhard Egger, Suhas Lohit +5
Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is…
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
Xiangyu Chen, Jing Liu, Ye Wang +4
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models fo…
Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?
Andrew Lowy, Zhuohang Li, Jing Liu +3
For small privacy parameter , -differential privacy (DP) provides a strong worst-case guarantee that no membership inference attack (MIA) can succeed at determining whether a…