5 citations · 12 across the 14 of their papers we have counts for
17 papers
Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge
Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio André Machado Porto
Brazilian Portuguese remains underserved by open-source language models, and the few that are safety-aligned rarely document what did not work or validate comparisons with statisti…
WorldOlympiad: Can Your World Model Survive a Triathlon?
Yuke Zhao, Wangbo Zhao, Weijie Wang +8
We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fidelity. While existing benchm…
ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation
Akide Liu, Jinbo Xing, Chaojie Mao +8
Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challenge: single-shot extrapolation p…
CoV: Chain-of-View Prompting for Spatial Reasoning
Haoyu Zhao, Akide Liu, Zeyu Zhang +5
Embodied question answering (EQA) in 3D environments often requires collecting context that is distributed across multiple viewpoints and partially occluded. However, most recent v…
OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
Feng Chen, Yefei He, Shaoxuan He +9
Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge t…
Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
Zihan Wang, Zhiyong Ma, Zhongkui Ma +5
Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose…
An Empirical Study on How Video-LLMs Answer Video Questions
Chenhui Gou, Ziyu Ma, Zicheng Duan +6
Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However,…
FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
Akide Liu, Zeyu Zhang, Zhexin Li +12
Diffusion generative models have become the standard for producing high-quality, coherent video content, yet their slow inference speeds and high computational demands hinder pract…
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
Weijie Wang, Donny Y. Chen, Zeyu Zhang +3
Feed-forward 3D Gaussian Splatting (3DGS) models have recently emerged as a promising solution for novel view synthesis, enabling one-pass inference without the need for per-scene…
CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation
Jinchao Ge, Bowen Zhang, Akide Liu +4
Class-incremental semantic segmentation (CSS) requires that a model learn to segment new classes without forgetting how to segment previous ones: this is typically achieved by dist…
KMM: Key Frame Mask Mamba for Extended Motion Generation
Zeyu Zhang, Hang Gao, Akide Liu +9
Human motion generation is a cut-edge area of research in generative computer vision, with promising applications in video creation, game development, and robotic manipulation. The…
ESA: Annotation-Efficient Active Learning for Semantic Segmentation
Jinchao Ge, Zeyu Zhang, Minh Hieu Phan +4
Active learning enhances annotation efficiency by selecting the most revealing samples for labeling, thereby reducing reliance on extensive human input. Previous methods in semanti…
InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation
Zeyu Zhang, Akide Liu, Qi Chen +5
Text-to-motion generation holds potential for film, gaming, and robotics, yet current methods often prioritize short motion generation, making it challenging to produce long motion…
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Akide Liu, Jing Liu, Zizheng Pan +3
A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously g…
Motion Mamba: Efficient and Long Sequence Motion Generation
Zeyu Zhang, Akide Liu, Ian Reid +3
Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent adv…
External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback
Akide Liu
Memory is identified as a crucial human faculty that allows for the retention of visual and linguistic information within the hippocampus and neurons in the brain, which can subseq…
CV 3315 Is All You Need : Semantic Segmentation Competition
Akide Liu, Zihan Wang
This competition focus on Urban-Sense Segmentation based on the vehicle camera view. Class highly unbalanced Urban-Sense images dataset challenge the existing solutions and further…