Tootfinder

SoK: Evaluating Jailbreak Guardrails for Large Language Models
Xunguang Wang, Zhenlan Ji, Wenxuan Wang, Zongjie Li, Daoyuan Wu, Shuai Wang
https://arxiv.org/abs/2506.10597

SoK: Evaluating Jailbreak Guardrails for Large Language Models
Large Language Models (LLMs) have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense mechanisms that monitor and control LLM interaction--have emerged as a promising solution. However, the current landscape of LLM guardrails is fragmented, lacking a unified taxonomy and comprehensive evaluation framework. In this Systematization of Knowledge (SoK) paper, we pre…

I honestly wonder how the famously right-wing leadership of Home Depot feel about having their workforce specifically targeted, terrorized, and (presumably) encouraged to seek work elsewhere. I doubt they care about these people as human beings, but surely they care about their labor costs. Have we heard any remarks from them? From their shareholders?

InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
Zhenzhi Wang, Jiaqi Yang, Jianwen Jiang, Chao Liang, Gaojie Lin, Zerong Zheng, Ceyuan Yang, Dahua Lin
https://arxiv.org/abs/2506.09984

InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could only animate a single subject and inject conditions in a global manner, ignoring scenarios that multiple concepts could appears in the same video with rich human-human interactions and human-object interactions. Such global assumption prevents precise and per-identity control of multiple concepts including humans and …

LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
Songze Li, Chuokun Xu, Jiaying Wang, Xueluan Gong, Chen Chen, Jirui Zhang, Jun Wang, Kwok-Yan Lam, Shouling Ji
https://arxiv.org/abs/2506.09443

LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge
Large Language Models (LLMs) have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial attacks that can manipulate evaluation outcomes, raising concerns about their robustness and, consequently, their trustworthiness. Existing evaluation methods adopted by LLM-based judges are often pie…

Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding
Xihua Sheng, Peilin Chen, Meng Wang, Li Zhang, Shiqi Wang, Dapeng Oliver Wu
https://arxiv.org/abs/2506.07709

Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding
With the remarkable progress in neural P-frame video coding, neural B-frame coding has recently emerged as a critical research direction. However, most existing neural B-frame codecs directly adopt P-frame coding tools without adequately addressing the unique challenges of B-frame compression, leading to suboptimal performance. To bridge this gap, we propose novel enhancements for motion compression and temporal fusion for neural B-frame coding. First, we design a fine-grained motion compressio…

KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Eugenie Lai, Gerardo Vitagliano, Ziyu Zhang, Sivaprasad Sudhir, Om Chabra, Anna Zeng, Anton A. Zabreyko, Chenning Li, Ferdi Kossmann, Jialin Ding, Jun Chen, Markos Markakis, Matthew Russo, Weiyang Wang, Ziniu Wu, Michael J. Cafarella, Lei Cao, Samuel Madden, Tim Kraska

KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes
Constructing real-world data-to-insight pipelines often involves data extraction from data lakes, data integration across heterogeneous data sources, and diverse operations from data cleaning to analysis. The design and implementation of data science pipelines require domain knowledge, technical expertise, and even project-specific insights. AI systems have shown remarkable reasoning, coding, and understanding capabilities. However, it remains unclear to what extent these capabilities translate…

Teaching Physical Awareness to LLMs through Sounds
Weiguo Wang, Andy Nie, Wenrui Zhou, Yi Kai, Chengchen Hu
https://arxiv.org/abs/2506.08524 https://

Teaching Physical Awareness to LLMs through Sounds
Large Language Models (LLMs) have shown remarkable capabilities in text and multimodal processing, yet they fundamentally lack physical awareness--understanding of real-world physical phenomena. In this work, we present ACORN, a framework that teaches LLMs physical awareness through sound, focusing on fundamental physical phenomena like the Doppler effect, multipath effect, and spatial relationships. To overcome data scarcity, ACORN introduce a physics-based simulator combining real-world sound…

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
JingLi Lin, Chenming Zhu, Runsen Xu, Xiaohan Mao, Xihui Liu, Tai Wang, Jiangmiao Pang
https://arxiv.org/abs/2507.07984

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
Recent advances in multimodal large language models (MLLMs) have shown remarkable capabilities in integrating vision and language for complex reasoning. While most existing benchmarks evaluate models under offline settings with a fixed set of pre-recorded inputs, we introduce OST-Bench, a benchmark designed to evaluate Online Spatio-Temporal understanding from the perspective of an agent actively exploring a scene. The Online aspect emphasizes the need to process and reason over incrementally a…

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Yana Wei, Liang Zhao, Jianjian Sun, Kangheng Lin, Jisheng Yin, Jingcheng Hu, Yinmin Zhang, En Yu, Haoran Lv, Zejia Weng, Jia Wang, Chunrui Han, Yuang Peng, Qi Han, Zheng Ge, Xiangyu Zhang, Daxin Jiang, Vishal M. Patel
https://arxiv.org/abs/2507…

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2.5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1,000 steps, surpassing all previous open-source effo…

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Hui Li, Pengfei Yang, Juanyang Chen, Le Dong, Yanxin Chen, Quan Wang
https://arxiv.org/abs/2507.07015

MST-Distill: Mixture of Specialized Teachers for Cross-Modal Knowledge Distillation
Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and statistical heterogeneities, failing to leverage the complementary prior knowledge embedded in cross-modal teacher models. This paper empirically reveals two critical issues in existing approaches: distillation path selection and knowledge drift. To address …