8 papers
MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation
Yansong Liu, Litong Gong, Weijie Li +2
Text-to-video (T2V) diffusion models have made remarkable progress in generating high-fidelity visuals, yet their outputs still often exhibit physically implausible phenomena, incl…
Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
Hongwei Zhao, Rui Liu, Yansong Liu
Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models re…
Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning
Hongwei Zhao, Rui Liu, Yansong Liu +2
Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previously learned ones. Although…
Strategy-Aware Optimization Modeling with Reasoning LLMs
Ruiqing Zhao, Fengzhi Li, Yuan Zuo +5
Large language models (LLMs) can generate syntactically valid optimization programs, yet often struggle to reliably choose an effective modeling strategy, leading to incorrect form…
Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
Fengzhi Li, Liang Zhang, Yuan Zuo +5
Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen…
RISE-T2V: Rephrasing and Injecting Semantics with LLM for Expansive Text-to-Video Generation
Xiangjun Zhang, Litong Gong, Yinglin Zheng +6
Most text-to-video(T2V) diffusion models depend on pre-trained text encoders for semantic alignment, yet they often fail to maintain video quality when provided with concise prompt…
Enhancing Speech Large Language Models through Reinforced Behavior Alignment
Yansong Liu, Jiateng Li, Yuan Liu
Speech large language models (SpeechLMs) can process spoken requests, yet still lag behind text-prompted large language models (LLMs) on instruction following and reasoning. We arg…
MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability
Buyu Liu, Kai Wang, Yansong Liu +3
This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack…