87 citations · 202 across the 51 of their papers we have counts for
53 papers
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
Ping Wu, Haibo Tong, Feifei Zhao +7
A common way to improve jailbreak robustness is to train on harmful requests rewritten as role-play, translation, or other forms. When used only for harmful requests, these forms m…
From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
Guobin Shen, Lei Huang, Xiang Cheng +4
On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback to serve as its own teacher…
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Guobin Shen, Xiang Cheng, Chenxiao Zhao +4
On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising directi…
AI Alignment Amplifies the Role of Race, Gender, and Disability in Hiring Decisions
Ze Wang, Guobin Shen, Michael Thaler
Humans increasingly delegate consequential decisions to language models, yet whether these systems reproduce or reshape human patterns of discrimination remains unclear. Here, acro…
Wearable AI in the Era of Large Sensor Models
Yize Cai, Baoshen Guo, Guobin Shen +1
As an effective approach to understanding the human-centric physical world, Wearable Artificial Intelligence (AI), which leverages multimodal wearable sensors to understand human p…
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Lei Huang, Xiang Cheng, Chenxiao Zhao +6
Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorit…
Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
Sicheng Shen, Mingyang Lv, Han Shen +7
The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved throu…
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Guobin Shen, Chenxiao Zhao, Xiang Cheng +2
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between trainin…
FireFly-P: FPGA-Accelerated Spiking Neural Network Plasticity for Robust Adaptive Control
Tenglong Li, Jindong Li, Guobin Shen +3
Spiking Neural Networks (SNNs) offer a biologically plausible learning mechanism through synaptic plasticity, enabling unsupervised adaptation without the computational overhead of…
TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers
Sicheng Shen, Mingyang Lv, Bing Han +4
In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence mode…
Efficient LLM Safety Evaluation through Multi-Agent Debate
Dachuan Lin, Guobin Shen, Zihao Yang +3
Safety evaluation of large language models (LLMs) increasingly relies on LLM-as-a-judge pipelines, but strong judges can still be expensive to use at scale. We study whether struct…
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense
Guobin Shen, Dongcheng Zhao, Haibo Tong +3
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it difficult to obtain effective tr…
Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
Haibo Tong, Dongcheng Zhao, Guobin Shen +4
The remarkable capabilities of Large Language Models (LLMs) have raised significant safety concerns, particularly regarding "jailbreak" attacks that exploit adversarial prompts to…
DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
Yao Liang, Dongcheng Zhao, Feifei Zhao +4
Aligning large language models (LLMs) with diverse human values is essential for safe and effective deployment, yet existing benchmarks often overlook cultural and demographic vari…
Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining
Bing Han, Feifei Zhao, Dongcheng Zhao +4
While fine-tuning services drive the rapid expansion of task capabilities in large language models (LLMs), they are often accompanied by the degradation and reorganization of safet…
Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA
Jindong Li, Tenglong Li, Ruiqi Chen +4
Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardwar…
Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
Guobin Shen, Dongcheng Zhao, Yiting Dong +2
Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evoluti…
C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Ping Wu, Guobin Shen, Dongcheng Zhao +6
Aligning LLMs with Chinese values requires culturally grounded resources that connect abstract values to concrete behavioral guidance. We introduce C-VARC, a Chinese Value Rule Cor…
PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
Guobin Shen, Dongcheng Zhao, Linghao Feng +8
Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit ha…
FireFly-T: High-Throughput Sparsity Exploitation for Spiking Transformer Acceleration with Dual-Engine Overlay Architecture
Tenglong Li, Jindong Li, Guobin Shen +3
Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transf…
STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking
Sicheng Shen, Dongcheng Zhao, Linghao Feng +5
Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. How…
Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning
Xiang He, Dongcheng Zhao, Yiting Dong +3
Humans interpret and perceive the world by integrating sensory information from multiple modalities, such as vision and hearing. Spiking Neural Networks (SNNs), as brain-inspired c…
Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA
Jindong Li, Tenglong Li, Guobin Shen +3
The extremely high computational and storage demands of large language models have excluded most edge devices, which were widely used for efficient machine learning, from being via…
: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility
Guobin Shen, Jindong Li, Tenglong Li +2
Spiking Neural Networks (SNNs) hold promise for energy-efficient, biologically inspired computing. We identify substantial informatio loss during spike transmission, linked to temp…