10 citations · 12 across the 16 of their papers we have counts for
17 papers
RIFAR: Reliability-Informed and Forgetting-Aware Replay for Continual Robot Learning with World-Action Models
Zirui Song, Tu Lin, Zirong Song +11
Genuine embodied agency requires robots to turn continuous real-world experience into lasting, transferable skills. This demands continual learning that integrates new capabilities…
Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation
Fengxian Ji, Yuke Li, Jingpu Yang +8
However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open question. To address this que…
Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory
Fengxian Ji, Zhuohan Xie, Jingpu Yang +3
With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often introduce additional training,…
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
Xianhui Meng, Zirui Song, Yuchen Zhang +10
Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible…
The Cylindrical Representation Hypothesis for Language Model Steering
Lang Gao, Jinghui Zhang, Wei Liu +7
Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based o…
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
Puning Yang, Junchi Yu, Qizhou Wang +3
Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which eras…
TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
Mingxuan Cui, Jingpu Yang, Fengxian Ji +7
Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level stru…
FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting
Fengxian Ji, Jingpu Yang, Zirui Song +5
Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluations offer limited coverage,…
ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services
Fengxian Ji, Jingpu Yang, Zirui Song +5
Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-wor…
FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation
Liuzhou Zhang, Zeyu Zhang, Biao Wu +10
Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often re…
FineState-Bench: A Comprehensive Benchmark for Fine-Grained State Control in GUI Agents
Fengxian Ji, Jingpu Yang, Zirui Song +6
With the rapid advancement of generative artificial intelligence technology, Graphical User Interface (GUI) agents have demonstrated tremendous potential for autonomously managing…
Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games
Xiaoqing Zhang, Huabin Zheng, Ang Lv +5
Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL), resembling an ``aha moment'' triggered by simpl…
ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models
Zirui Song, Guangxian Ouyang, Mingzhe Li +10
Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing…
Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework
Zirui Song, Jingpu Yang, Yuan Huang +6
Geolocation, the task of identifying an image's location, requires complex reasoning and is crucial for navigation, monitoring, and cultural preservation. However, current methods…
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey
Zirui Song, Bin Yan, Yuhan Liu +4
Large Language Models (LLMs) have demonstrated remarkable success in various tasks such as natural language understanding, text summarization, and machine translation. However, the…
Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies
Zirui Song, Guangxian Ouyang, Meng Fang +9
Existing household robots have made significant progress in performing routine tasks, such as cleaning floors or delivering objects. However, a key limitation of these robots is th…
MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot
Zirui Song, Yaohang Li, Meng Fang +6
Large language model agents that interact with PC applications often face limitations due to their singular mode of interaction with real-world environments, leading to restricted…