29 citations · 42 across the 31 of their papers we have counts for
11 papers · 1 filter
RoboOmni: Proactive Robot Manipulation in Omni-modal Context
Siyin Wang, Jinlan Fu, Feihong Liu +11
Recent advances in Multimodal Large Language Models (MLLMs) have driven rapid progress in Vision-Language-Action (VLA) models for robotic manipulation. Although effective in many s…
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
Xingjian Zhao, Zhe Xu, Qinyuan Cheng +20
Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits exp…
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
Senyu Fei, Siyin Wang, Junhao Shi +10
Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform…
CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation
Ruifan Deng, Yitian Gong, Qinghui Gao +5
With the rise of multimodal large language models (LLMs), audio codec plays an increasingly vital role in encoding audio into discrete tokens, enabling integration of audio into te…
XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
Yitian Gong, Luozhijie Jin, Ruifan Deng +6
Speech codecs serve as bridges between speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also ca…
World-aware Planning Narratives Enhance Large Vision-Language Model Planner
Junhao Shi, Zhaoye Fei, Siyin Wang +3
Large Vision-Language Models (LVLMs) show promise for embodied planning tasks but struggle with complex scenarios involving unfamiliar environments and multi-step goals. Current ap…
Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
Zhaoye Fei, Li Ji, Siyin Wang +3
Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they face significant challenges in embodied task planning scenarios that require c…
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
Kexin Huang, Qian Tu, Liwei Fan +6
In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mer…
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Yikun Wang, Siyin Wang, Qinyuan Cheng +5
Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typi…
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
Siyin Wang, Zhaoye Fei, Qinyuan Cheng +4
Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and…
How to Mitigate Overfitting in Weak-to-strong Generalization?
Junhao Shi, Qinyuan Cheng, Zhaoye Fei +3
Aligning powerful AI models on tasks that surpass human evaluation capabilities is the central problem of \textbf{superalignment}. To address this problem, weak-to-strong generaliz…