11 papers
Anti-Shortcut Distillation via Temporal Negative Knowledge Transfer
Syed Muhammad Raza, Omer Tariq, Jeongbae Son
Knowledge distillation (KD) trains a compact student by attracting it towards a converged teacher. It is silent about which directions the teacher itself learned to suppress: repul…
Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning
Kaiwen Chen, Shuhai Zhang, Zimo Liu +7
Large-scale neural network training increasingly relies on matrix-aware optimizers that exploit the structure of weight parameters beyond element-wise adaptation. However, existing…
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
Jiahao Yang, Shuhai Zhang, Hailong Kang +3
Large language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content, posing significant risks to their safe use. Detecting such hallucinations is…
ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse
Guohao Chen, Shuaicheng Niu, Deyu Chen +5
Test-time entropy minimization helps adapt a model to novel environments and incentivize its reasoning capability, unleashing the model's potential during inference by allowing it…
Latent-Condensed Transformer for Efficient Long Context Modeling
Zeng You, Yaofo Chen, Qiuwu Chen +5
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention…
ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models
Wei Luo, Yangfan Ou, Jin Deng +4
Large-scale Vision-Language Models (VLMs) exhibit strong zero-shot recognition, yet their real-world deployment is challenged by distribution shifts. While Test-Time Adaptation (TT…