1 citations · 1 across the 14 of their papers we have counts for
9 papers · 1 filter
Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness
Yi Chen, Hanna Hsieh, Shuhong Liu +4
Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed knowledge. Existing robustness p…
OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation
Jiakai Tang, Sunhao Dai, Kun Wang +8
Multi-task learning (MTL) is essential in recommender systems to enable complementary learning among diverse user feedback. While modern industrial practices have shifted from DNNs…
Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion
ShiYing Huang, Liang Lin, Yuer Li +6
In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tensi…
Mem-W: Latent Memory-Native GUI Agents
Guibin Zhang, Yaohui Ling, Fanci Meng +2
GUI agents are beginning to operate the web, mobile, and desktop as interactive worlds, where successful control depends on carrying forward visual, procedural, and task-level evid…
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks
Kun Wang, Reinhard Heckel
Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approa…
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Jiahao Wu, Ning Lu, Shengcai Liu +6
Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance perfor…
MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
Zhengwei Xie, Zhisheng Chen, Ziyan Weng +7
Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to tran…
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Wi…