3 citations · 3 across the 13 of their papers we have counts for
10 papers · 1 filter
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
Yunbo Tang, Chengyi Yang, Shiyu Liu +4
Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a criti…
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Yujie Lin, Chengyi Yang, Zhishang Xiang +2
Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for p…
ParaTool: Shifting Tool Representations from Context to Parameters
Zekai Yu, Qi Meng, Qizhi Chu +3
Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. Howe…
On the Robustness of Machine Unlearning for Vision-Language Models
Yujie Lin, Kaidi Jia, Jiayao Ma +2
Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work, we present the first systema…
CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models
Hsiang-Wei Huang, Junbin Lu, Kuang-Ming Chen +3
Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect genuine spatial intelligence. W…
Latent Action Reparameterization for Efficient Agent Inference
Wenhao Huang, Qingwen Zeng, Qiyue Chen +11
Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior wor…
Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
Kaidi Jia, Yujie Lin, Chengyi Yang +2
Vision-language models (VLMs) raise growing concerns about privacy, copyright, and bias, motivating machine unlearning to remove sensitive knowledge. However, existing methods prim…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
Chengyi Yang, Pengzhen Li, Jiayin Qi +3
Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated b…
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Chengyi Yang, Zhishang Xiang, Yunbo Tang +5
Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. However, existing me…