5 citations · 17 across the 27 of their papers we have counts for
27 papers
CompassOPD: Cross-Family On-Policy Distillation via Within-Family Likelihood Shifts
Naibin Gu, Qingyi Si, Chenxu Yang +5
On-policy distillation (OPD) provides dense token-level supervision on student-generated trajectories. Although OPD performs strongly when teacher and student belong to the same mo…
CoRe-MoE: Compact Reusable MoE for Continual Multimodal Instruction Tuning
Runze Liu, Naibin Gu, Mingxu Ai +4
Continual multimodal instruction tuning requires multimodal large language models to acquire new task abilities sequentially while preserving previously learned knowledge. LoRA-MoE…
Hallucinations Leave a Grounding Signature:Verifier-Guided Decoding for Selective Object Correction
Lei Yang, Xinze Liu, Dayan Wu +7
Large vision-language models (LVLMs) often hallucinate objects that are absent from an image. Despite recent progress, existing mitigation methods still lack reliable object-level…
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR
Chuanyu Qin, Chenxu Yang, Qingyi Si +3
Reinforcement learning with verifiable rewards (RLVR) improves the ability of large language model, yet headline accuracy gains often conceal a hidden cost: previously solved probl…
Co-Evolving Policy Distillation
Naibin Gu, Chenxu Yang, Qingyi Si +7
RLVR and OPD have become standard paradigms for post-training. We provide a unified analysis of these two paradigms in consolidating multiple expert capabilities into a single mode…
Learning from the Near Future: Temporal Self-Distillation for RLVR
Chuanyu Qin, Chenxu Yang, Qingyi Si +6
Reinforcement learning with verifiable rewards (RLVR) is a core post-training recipe for reasoning models, yet pure on-policy learning can be inefficient when useful trajectories a…
EasyVideoR1: Easier RL for Video Understanding
Chuanyu Qin, Chenxu Yang, Qingyi Si +6
Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve i…
Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding
Yuchen Feng, Zhenyu Zhang, Naibin Gu +8
Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, per…
CBP-Tuning: Efficient Local Customization for Black-box Large Language Models
Jiaxuan Zhao, Naibin Gu, Yuchen Feng +4
The high costs of customizing large language models (LLMs) fundamentally limit their adaptability to user-specific needs. Consequently, LLMs are increasingly offered as cloud-based…
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
Naibin Gu, Zhenyu Zhang, Yuchen Feng +8
Mixture-of-Experts (MoE) models typically fix the number of activated experts at both training and inference. However, real-world deployments often face heterogeneous hardware,…
DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts
Yuchen Feng, Bowen Shen, Naibin Gu +4
Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference…
Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models
Naibin Gu, Peng Fu, Xiyu Liu +3
Parameter-efficient fine-tuning (PEFT) has become a common method for fine-tuning large language models, where a base model can serve multiple users through PEFT module switching.…
Advantageous Parameter Expansion Training Makes Better Large Language Models
Naibin Gu, Yilong Chen, Zhenyu Zhang +7
Although scaling up the number of trainable parameters can effectively improve the training performance of large language models, it also leads to increased computational overhead.…
BeamLoRA: Beam-Constraint Low-Rank Adaptation
Naibin Gu, Zhenyu Zhang, Xiyu Liu +7
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tunin…
Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering
Peize Li, Qingyi Si, Peng Fu +2
Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "ret…
Think out Loud: Emotion Deducing Explanation in Dialogues
Jiangnan Li, Zheng Lin, Lanrui Wang +6
Humans convey emotions through daily dialogues, making emotion understanding a crucial step of affective intelligence. To understand emotions in dialogues, machines are asked to re…
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
Naibin Gu, Peng Fu, Xiyu Liu +3
Parameter-efficient fine-tuning (PEFT) has emerged as the predominant technique for fine-tuning in the era of large language models. However, existing PEFT methods still have inade…
Are Large Language Models Table-based Fact-Checkers?
Hanwen Zhang, Qingyi Si, Peng Fu +2
Table-based Fact Verification (TFV) aims to extract the entailment relation between statements and structured tables. Existing TFV methods based on small-scaled models suffer from…
Object Attribute Matters in Visual Question Answering
Peize Li, Qingyi Si, Peng Fu +2
Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. However, integrating visual and textual semantics solely thr…
Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension
Jiangnan Li, Mo Yu, Fandong Meng +4
In this work, we focus on dialogue reading comprehension (DRC), a task extracting answer spans for questions from dialogues. Dialogue context modeling in DRC is tricky due to compl…
A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models
Yuanxin Liu, Fandong Meng, Zheng Lin +5
Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and compu…
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA
Qingyi Si, Fandong Meng, Mingyu Zheng +6
Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution. To evaluate the VQA models' reasoning ab…
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
Qingyi Si, Yuanxin Liu, Fandong Meng +5
Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them br…
Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering
Qingyi Si, Yuanxin Liu, Zheng Lin +2
Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language b…