JS
Jingbo Shang
cs.CLcs.AIcs.LGcs.CVcs.IRcs.SIstat.MLBrainChromatincs.HC
On Valency
published · living versionsW_472urbcs·v1 · currentpublished
FrontierCS 2: A Benchmark for Computer Science R&D
with Qiuyang Mang, Wenhao Chai, Runyuan He, Dongruixuan Li +56
1 version
Preprints & journals
177 papers in the corpus · 2014–2026FrontierCS 2: A Benchmark for Computer Science R&D2610.29932v1 · Qiuyang Mang, Wenhao Chai, Runyuan He et al.2026 · 0 citationsarXivon Valency
DISCERN: Can AI Agents Work Like Scientists and Guide Discovery?2609.33357v2 · Nan Huang, Mario Tapia-Pacheco, Kun Zhou et al.2026 · 0 citationsarXiv
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States2609.15972v1 · Zixuan Wang, Yufan Zhou, Jinzhou Tang et al.2026 · 0 citationsarXiv
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?2609.01552v2 · Yiming Huang, Ziche Liu, Junxia Cui et al.2026 · 0 citationsarXiv
SimSD: Simple Speculative Decoding in Diffusion Language Models2606.02544v2 · Junxia Cui, Haotian Ye, Runchu Tian et al.2026 · 0 citationsarXiv
CoMem: Context Management with A Decoupled Long-Context Model2605.30842v1 · Yuwei Zhang, Chengyu Dong, Shuowei Jin et al.2026 · 0 citationsarXiv
TIER: Trajectory-Invariant Execution Rewards for Multi-Step Tool Composition2605.16790v1 · Anay Kulkarni, ChiaEn Lu, Dheeraj Mekala et al.2026 · 0 citationsarXiv
ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation2605.12857v1 · Zhongkai Yu, Yichen Lin, Chenyang Zhou et al.2026 · 0 citationsarXiv
F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking2605.12995v1 · Rohan Surana, Gagan Mundada, Junda Wu et al.2026 · 0 citationsarXiv
Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation2605.12741v1 · Yuwei Zhang, Sha Li, Changlong Yu et al.2026 · 0 citationsarXiv
MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization2605.10784v1 · Rohan Surana, Xintong Li, Sheldon Yu et al.2026 · 0 citationsarXiv
OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents2605.11169v1 · Sheldon Yu, Junda Wu, Xintong Li et al.2026 · 0 citationsarXiv
Skill-R1: Agent Skill Evolution via Reinforcement Learning2605.09359v1 · Yash Vishe, Rohan Surana, Xunyi Jiang et al.2026 · 0 citationsarXiv
CocoaBench: Evaluating Unified Digital Agents in the Wild2604.11201v2 · CocoaBench Team: Shibo Hao, Zhining Zhang, Zhiqi Liang et al.2026 · 0 citationsarXiv
Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis2604.09874v2 · Xinkai Zou, Yiming Huang, Zhuohang Wu et al.2026 · 0 citationsarXiv
EvoLen: Evolution-Guided Tokenization for DNA Language Model2604.08698v3 · Nan Huang, Xiaoxiao Zhou, Junxia Cui et al.2026 · 0 citationsarXiv
How Well Does Generative Recommendation Generalize?2603.19809v1 · Yijie Ding, Zitian Guo, Jiacheng Li et al.2026 · 0 citationsarXiv
SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans2603.07853v1 · Hansi Zeng, Zoey Li, Yifan Gao et al.2026 · 0 citationsarXiv
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning2603.00296v1 · Xintong Li, Sha Li, Rongmei Lin et al.2026 · 0 citationsarXiv
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning2602.17025v1 · Gagan Mundada, Zihan Huang, Rohan Surana et al.2026 · 0 citationsarXiv
AMPS: Adaptive Modality Preference Steering via Functional Entropy2602.12533v1 · Zihan Huang, Xintong Li, Rohan Surana et al.2026 · 0 citationsarXiv
Codified Finite-state Machines for Role-playing2602.05905v1 · Letian Peng, Yupeng Hou, Kun Zhou et al.2026 · 0 citationsarXiv
Deriving Character Logic from Storyline as Codified Decision Trees2601.10080v1 · Letian Peng, Kun Zhou, Longfei Yun et al.2026 · 0 citationsarXiv
Codified Foreshadowing-Payoff Text Generation2601.07033v1 · Longfei Yun, Kun Zhou, Yupeng Hou et al.2026 · 0 citationsarXiv
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes2601.05600v1 · Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang et al.2026 · 0 citationsarXiv
Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills2512.16301v3 · Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi et al.2025 · 1 citationarXiv
DNAMotifTokenizer: Towards Biologically Informed Tokenization of Genomic Sequences2512.17126v2 · Xiaoxiao Zhou, Zihan Wang, Jingbo Shang et al.2025 · 0 citationsarXiv
Watermarks for Language Models via Probabilistic Automata2512.10185v1 · Yangkun Wang, Jingbo Shang2025 · 0 citationsarXiv
Order Matters: Rethinking Prompt Construction in In-Context Learning2511.09700v1 · Warren Li, Yiqian Wang, Zihan Wang et al.2025 · 0 citationsarXiv
Contamination Detection for VLMs using Multi-Modal Semantic Perturbation2511.03774v2 · Jaden Park, Mu Cai, Feng Yao et al.2025 · 0 citationsarXiv
Train a Unified Multimodal Data Quality Classifier with Synthetic Data2510.15162v1 · Weizhi Wang, Rongmei Lin, Shiyang Li et al.2025 · 0 citationsarXiv
Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Models2510.05090v1 · Runchu Tian, Junxia Cui, Xueqiang Xu et al.2025 · 0 citationsarXiv
A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining2510.01427v4 · Sipeng Zhang, Longfei Yun, Zilong Wang et al.2025 · 0 citationsarXiv
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics2509.00190v2 · Sheldon Yu, Yuxin Xiong, Junda Wu et al.2025 · 0 citationsarXiv
ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation2506.23041v1 · Chengyu Dong, Huan Gui, Noveen Sachdeva et al.2025 · 0 citationsarXiv
From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents2506.18959v3 · Weizhi Zhang, Yangning Li, Yuanchen Bei et al.2025 · 0 citationsarXiv
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents2506.06254v2 · Weizhi Zhang, Xinyang Zhang, Chenwei Zhang et al.2025 · 1 citationarXiv
Training Language Models to Generate Quality Code with Program Analysis Feedback2505.22704v1 · Feng Yao, Zilong Wang, Liyuan Liu et al.2025 · 0 citationsarXiv
RRO: LLM Agent Optimization Through Rising Reward Trajectories2505.20737v1 · Zilong Wang, Jingfeng Yang, Sreyashi Nag et al.2025 · 1 citationarXiv
The Price of Format: Diversity Collapse in LLMs2505.18949v1 · Longfei Yun, Chenyang An, Zilong Wang et al.2025 · 5 citationsarXiv
Text Generation Beyond Discrete Token Sampling2505.14827v3 · Yufan Zhuang, Liyuan Liu, Chandan Singh et al.2025 · 0 citationsarXiv
Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection2505.12306v1 · Yuwei Zhang, Wenhao Yu, Shangbin Feng et al.2025 · 0 citationsarXiv
Codifying Character Logic in Role-Playing2505.07705v2 · Letian Peng, Jingbo Shang2025 · 0 citationsarXiv
A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models2504.07070v1 · Zhouhang Xie, Junda Wu, Yiran Shen et al.2025 · 0 citationsarXiv
Tuning LLMs by RAG Principles: Towards LLM-native Memory2503.16071v1 · Jiale Wei, Shuchi Wu, Ruochen Liu et al.2025 · 0 citationsarXiv
Can Language Models Follow Multiple Turns of Entangled Instructions?2503.13222v3 · Chi Han, Xin Liu, Haodong Wang et al.2025 · 0 citationsarXiv
Matching Skeleton-based Activity Representations with Heterogeneous Signals for HAR2503.14547v1 · Shuheng Li, Jiayun Zhang, Xiaohan Fu et al.2025 · 3 citationsarXiv
Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval2503.09819v1 · Yuwei Zhang, Jayanth Srinivasa, Gaowen Liu et al.2025 · 0 citationsarXiv
AI-native Memory 2.0: Second Me2503.08102v2 · Jiale Wei, Xiang Ying, Tao Gao et al.2025 · 0 citationsarXiv
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning2503.07018v1 · Xintong Li, Jalend Bantupalli, Ria Dharmani et al.2025 · 0 citationsarXiv
Career total: 237 works. 177 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.