1 citations · 3 across the 9 of their papers we have counts for
9 papers
To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
Haoqing Wang, Xiang Long, Ziheng Li +3
Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level…
Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
Hui Wu, Hengyi Cai, Jinman Zhao +6
Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training va…
Efficient Thought Space Exploration Through Strategic Intervention
Ziheng Li, Hengyi Cai, Xiaochi Wei +4
While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs by exhaustive samplin…
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Ziheng Li, Zexu Sun, Jinman Zhao +8
Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLV…
Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements
Ziheng Li, Zhi-Hong Deng
Although the LLM-based in-context learning (ICL) paradigm has demonstrated considerable success across various natural language processing tasks, it encounters challenges in event…
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Ziheng Li, Shaohan Huang, Zihan Zhang +7
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our…
Detachedly Learn a Classifier for Class-Incremental Learning
Ziheng Li, Shibo Jie, Zhi-Hong Deng
In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretra…
Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework
Gehui Shen, Shibo Jie, Ziheng Li +1
Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online con…
Alleviating Representational Shift for Continual Fine-tuning
Shibo Jie, Zhi-Hong Deng, Ziheng Li
We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultim…