10 citations · 27 across the 13 of their papers we have counts for
13 papers
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu +1
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises…
GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
Yuhan Wang, Siwei Yang, Bingchen Zhao +4
Recent advancements in large multimodal models like GPT-4o have set a new standard for high-fidelity, instruction-guided image editing. However, the proprietary nature of these mod…
: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark
Siwei Yang, Mude Hui, Bingchen Zhao +3
We introduce , a comprehensive benchmark designed to systematically evaluate instruction-based image editing models across instructions of varying complexity…
Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability
Haonan Li, Xudong Han, Zenan Zhai +32
To address this gap, we introduce Libra-Leaderboard, a comprehensive framework designed to rank LLMs through a balanced evaluation of performance and safety. Combining a dynamic le…
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
Yanqing Liu, Xianhang Li, Zeyu Wang +2
Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative…
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
Zijun Wang, Haoqin Tu, Jieru Mei +3
This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate…
What If We Recaption Billions of Web Images with LLaMA-3?
Xianhang Li, Haoqin Tu, Mude Hui +9
Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance…
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
Mude Hui, Siwei Yang, Bingchen Zhao +5
This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200,000 edits. Unlike prior approaches relying on attribute guidance or human feed…
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Bo Peng, Daniel Goldstein, Quentin Anthony +27
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-value…
AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability
Siwei Yang, Bingchen Zhao, Cihang Xie
This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts, such as depth-first sear…
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
Bingchen Zhao, Haoqin Tu, Chen Wei +2
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a do…
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Haoqin Tu, Chenhang Cui, Zijun Wang +6
This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different from prior studies, we shift our focus from evaluating standard performance to introducing…
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
Haoqin Tu, Bingchen Zhao, Chen Wei +1
Multi-modal large language models (MLLMs) are trained based on large language models (LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual respon…