6 citations · 20 across the 47 of their papers we have counts for
33 papers · 1 filter
Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation
Xincheng Wei, Yifan Ding, Yoshua Li +6
On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student-sampled prefixes. Standard…
What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMs
Ziran Li, Qiang Wang, Zhengyu Chen +4
Choosing the right large language model (LLM) backbone is the most consequential decision when building a vision-language model (VLM), yet it remains fundamentally unprincipled: co…
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Yuchun Fan, Bei Li, Peiguang Li +9
Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts.…
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
Junhao Ruan, Abudukeyumu Abudula, Bei Li +8
Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer…
Causal Autoregressive Diffusion Language Model
Junhao Ruan, Bei Li, Yongjing Yin +6
In this work, we propose Causal Autoregressive Diffusion (CARD), a novel framework that unifies the training efficiency of ARMs with the high-throughput inference of diffusion mode…
SpanNorm: Reconciling Training Stability and Performance in Deep Transformers
Chao Wang, Bei Li, Jiaqi Zhang +8
The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, lead…
A Preliminary Study on the Promises and Challenges of Native Top- Sparse Attention
Di Xiu, Hongyin Tang, Bolin Rong +4
Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hinder…
LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge Points
Xuemiao Zhang, Can Ren, Chengying Tu +4
The advancement of large language models (LLMs) struggles with the scarcity of high-quality, diverse training data. To address this limitation, we propose LinkSyn, a novel knowledg…
Large-Scale Diverse Synthesis for Mid-Training
Xuemiao Zhang, Chengying Tu, Can Ren +4
The scarcity of high-quality, knowledge-intensive training data hinders the development of large language models (LLMs), as traditional corpora provide limited information. Previou…
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
Zihao Wei, Liang Pang, Jiahao Liu +7
Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reaso…
Libra: Assessing and Improving Reward Model by Learning to Think
Meng Zhou, Bei Li, Jiahao Liu +5
Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenario…
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
Hexiang Tan, Fei Sun, Sha Liu +8
As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection…
Dynamic Fisher-weighted Model Merging via Bayesian Optimization
Sanwoo Lee, Jiahao Liu, Qifan Wang +3
The fine-tuning of pre-trained language models has resulted in the widespread availability of task-specific models. Model merging offers an efficient way to create multi-task model…
NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
Lanrui Wang, Mingyu Zheng, Hongyin Tang +5
Processing structured tabular data, particularly large and lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs). However, existing long-c…
SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
Xiangyu Xi, Deyang Kong, Jian Yang +7
Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and th…
Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective
Ruichen Shao, Bei Li, Gangao Liu +5
Direct Preference Optimization (DPO) has gained attention as an efficient alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs)…
FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
Xuemiao Zhang, Feiyu Duan, Liangyu Xu +5
Large language models (LLMs) have significantly advanced human language understanding and generation, with pretraining data quality and organization being crucial to their performa…
FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training
Liangyu Xu, Xuemiao Zhang, Feiyu Duan +4
Selecting high-quality data can improve the pretraining efficiency of large language models (LLMs). Existing methods generally rely on heuristic techniques or single quality signal…
Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern
Hongyin Tang, Di Xiu, Lanrui Wang +3
The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address t…
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
Bei Li, Tong Zheng, Rui Wang +8
Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep method…
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
Yiwen Ding, Zhiheng Xi, Wei He +7
Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effect…
FIRP: Faster LLM inference via future intermediate representation prediction
Pengfei Wu, Jiahao Liu, Zhuocheng Gong +5
Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which…
ReMamba: Equip Mamba with Effective Long-Sequence Modeling
Danlong Yuan, Jiahao Liu, Bei Li +4
While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence sug…
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
Muxi Diao, Rumei Li, Shiyang Liu +4
As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to…