11 papers
SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia
Jingyi Liao, Wenyu Zhang, Zhuohan Liu +6
The rapid advancement of audio and multimodal large language models has unlocked transformative speech understanding capabilities, yet evaluation frameworks remain predominantly En…
Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off
Longyin Zhang, Shuo Sun, Yingxu He +15
Recent advancements in Multimodal Large Language Models (MLLMs) pursue omni-perception capabilities, yet integrating robust sensory grounding with complex reasoning remains a chall…
SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
Wenhao Sun, Rong-Cheng Tu, Yifu Ding +4
While Diffusion Language Models (DLMs) offer a flexible, arbitrary-order alternative to the autoregressive paradigm, their non-causal nature precludes standard KV caching, forcing…
MERaLiON-SER: Robust Speech Emotion Recognition Model for English and SEA Languages
Hardik B. Sailor, Aw Ai Ti, Chen Fang Yih Nancy +26
We present MERaLiON-SER, a robust speech emotion recognition model designed for English and Southeast Asian languages. The model is trained using a hybrid objective combining weigh…
AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
Jingyi Liao, Yongyi Su, Rong-Cheng Tu +6
While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrain…
SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
Zhao Jin, Rong-Cheng Tu, Jingyi Liao +4
3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies…
MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval
Rong-Cheng Tu, Zhao Jin, Jingyi Liao +4
Existing Zero-Shot Composed Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens, which are concatenated with the modifyi…
VORTA: Efficient Video Diffusion via Routing Sparse Attention
Wenhao Sun, Rong-Cheng Tu, Yifu Ding +4
Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention o…
AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
Wenhao Sun, Rong-Cheng Tu, Jingyi Liao +2
Diffusion Transformers (DiTs) have proven effective in generating high-quality videos but are hindered by high computational costs. Existing video DiT sampling acceleration methods…
SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing
Rong-Cheng Tu, Wenhao Sun, Zhao Jin +3
While open-source video generation and editing models have made significant progress, individual models are typically limited to specific tasks, failing to meet the diverse needs o…
Diffusion Model-Based Video Editing: A Survey
Wenhao Sun, Rong-Cheng Tu, Jingyi Liao +1
The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editin…