1 citations · 1 across the 10 of their papers we have counts for
10 papers
Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks
Mingyu Luo, Ming Deng, Zilang Qiu +8
Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read…
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
Zhengbo Jiao, Yiming Cheng, Yilei Jiang +15
Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search…
Perceptual Flow Network for Visually Grounded Reasoning
Yangfu Li, Yuning Gong, Hongjian Zhan +8
Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories, leading to language bias an…
DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
JiYang Wang, Jiawei Chen, Mengqi Xiao +3
Object level hallucination remains a central reliability challenge for vision language models (VLMs), particularly in binary object existence verification. Existing benchmarks emph…
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
Teng Li, Ziyuan Huang, Cong Chen +5
We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruc…
StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision
Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng +7
Reasoning-based text-to-image (T2I) generation requires models to interpret complex prompts accurately. Existing reasoning frameworks can be broadly categorized into two types: (1)…
DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models
Yangfu Li, Hongjian Zhan, Jiawei Chen +3
Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bo…
Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering
Yangfu Li, Hongjian Zhan, Tianyi Chen +2
Existing visual token pruning methods target prompt alignment and visual preservation with static strategies, overlooking the varying relative importance of these objectives across…
DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification
Yangfu Li, Jiapan Gan, Xiaodan Lin
Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Exist…
PSVRF: Learning to restore Pitch-Shifted Voice without reference
Yangfu Li, Xiaodan Lin, Jiaxin Yang
Pitch scaling algorithms have a significant impact on the security of Automatic Speaker Verification (ASV) systems. Although numerous anti-spoofing algorithms have been proposed to…