影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
82.97/100
前 1.1%
全站排名 #720
发表论文23 篇
平均评分
年均产出7.7 篇/年
Lifeng Shang
研究方向
nlp · deep learning · rnn · BERT · pre-trained language models · dialogue · computer vision · topic models · facial expression · graphical models
11
From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
ICLR 2026Poster
通讯22
ATTS: Asynchronous Test-Time Scaling via Conformal Prediction
ICLR 2026Poster
13
Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
ICLR 2026Poster
24
ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction
ICLR 2026Poster
19
UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
ICLR 2026Poster
通讯21
ModalMix: Optimizing Multimodal Data Mixtures with Compute-Dependent Regression
ICLR 2026Rejected
11
Group Pattern Selection Optimal: Let LRMs Pick the Right Pattern for Reasoning
ICLR 2026Withdrawn
通讯5
DualRPO: All-in-one Visual RL with Internal and External Rewards
ICLR 2026Rejected
5
StructZip: Compressing Large-Scale Structured Prompts to One Token via Learning Natural Language Descriptions
ICLR 2026Rejected
通讯17
RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
NeurIPS 2025Spotlight
18
DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning
NeurIPS 2025Spotlight
通讯21
QFFT, Question-Free Fine-Tuning for Adaptive Reasoning
NeurIPS 2025Spotlight
11
Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
ICML 2025Poster
23
ToolACE: Winning the Points of LLM Function Calling
ICLR 2025Poster
22
Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
ICLR 2025Poster
32
RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
ICLR 2025Poster
26
Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape
ICLR 2025Rejected
40
Subtle Errors Matter: Preference Learning via Error-injected Self-editing
ICLR 2025Rejected