19 citations · 24 across the 19 of their papers we have counts for
9 papers · 1 filter
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Yukun Chen, Boheng Li, Yu Yuan +5
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to li…
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Jiaming Li, Longze Chen, Ze Gong +5
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and p…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…
DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
Shuo Shao, Yiming Li, Mengren Zheng +7
The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure reg…
STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation
Jiaming Li, Yukun Chen, Ziqiang Liu +10
Stories are central to human culture, serving to share ideas, preserve traditions, and foster connections. Automatic story generation, a key advancement in artificial intelligence…
Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models
Jiaming Li, Haoran Ye, Yukun Chen +5
Sparse Autoencoders (SAEs) are a cornerstone of mechanistic interpretability. Existing training methods inherit the Block Training paradigm from LLM pre-training, which introduces…
EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection
Ancheng Xu, Zhihao Yang, Jingpeng Li +9
E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading product content. However, these models rema…
StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
Yinmin Zhong, Zili Zhang, Xiaoniu Song +11
Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first ge…
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Yukun Chen, Shuo Shao, Enhao Huang +4
Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training…