19 citations · 24 across the 19 of their papers we have counts for
23 papers
Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
Kuan Zhang, Yukun Chen, Zhihao Yang +8
Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared physical laws. Whether these…
Towards Merging-conditional Backdoor Unalignment against Large Language Models
Yukun Chen, Yidou Chen, Yiming Li +4
Model merging has become widely adopted for enhancing the task-specific performance of Large Language Models (LLMs) without additional training. While the specialized model from th…
Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Kuan Zhang, Yukun Chen, Zhihao Yang +7
Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent und…
FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment
Qinhong Lin, Ruitao Feng, Yinglun Feng +7
We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly exec…
RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
Yukun Chen, Jiaming Li, Longze Chen +10
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying sol…
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
Yukun Chen, Xinyu Zhang, Boyi Deng +6
As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting th…
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…
PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation
Jing Luo, Longze Chen, Run Luo +12
While closed-source Large Language Models (LLMs) demonstrate strong mathematical problem-solving abilities, open-source models still face challenges with such tasks. To bridge this…
Optimizing RLHF Training for Large Language Models with Stage Fusion
Yinmin Zhong, Zili Zhang, Bingyang Wu +8
We present RLHFuse, an efficient training system with stage fusion for Reinforcement Learning from Human Feedback (RLHF). Due to the intrinsic nature of RLHF training, i.e., the da…
Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking
Xuewei Wang, Qiang Jin, Shengyu Huang +10
Dividing ads ranking system into retrieval, early, and final stages is a common practice in large scale ads recommendation to balance the efficiency and accuracy. The early stage r…
Boxhead: A Dataset for Learning Hierarchical Representations
Yukun Chen, Andrea Dittadi, Frederik Träuble +2
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks. However, a common assumption in learning disentangled representations is that the data genera…
Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion
Xinye Zheng, Jianbo Ye, Yukun Chen +5
Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Satellite imaginary data are in increasingly higher res…
Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
Yukun Chen, Jianbo Ye, Jia Li
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being…
A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration
Yukun Chen, Jianbo Ye, Jia Li
We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being…