12:30 - 12:50 報到

13:00 - 14:00 論文分享 Session 1

1. CooT 🐦: Learning to Coordinate In-Context with Coordination Transformers
   王懷志，電信所 博士生 (Robot Learning Lab)

2. Language-Critique Imitation Learning from Suboptimal Demonstrations
   楊智翰，電信所 碩士生 (Robot Learning Lab)

3. Robust Concept Unlearning in Diffusion Models via Directional Stability Regularization
   賴柏翰，資工所 博士生 (Artificial Intelligence Security Lab)

4. Adversarially Robust Federated Learning with Heterogeneous Computational Resources
   林東君，資工所 碩士生 (Artificial Intelligence Security Lab)

14:20 - 15:20 論文分享 Session 2

1. Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States
   簡翌， 電機系/電信所 助理教授

2. MIRA: Multimodal Interleaved Reasoning with Adaptive Visual Tokens
   王奎鈞，電信所 碩士生 (Vision and Learning Laboratory)

3. TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
   曾亮軒，電信所 博士生 (Speech Processing and ML Lab)

4. STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
   姜成翰，電機所 博士生 (Speech Processing and ML Lab)

15:40 - 16:40 Panel Session: 投稿及參加Conference的心得分享

Panelists:

1. 簡翌，電機系/電信所 助理教授

2. 廖家緯，資工所 博士生 (Communication and Multimedia Laboratory)

3. 曾亮軒，電信所 博士生 (Speech Processing and ML Lab)

4. 尤展鴻，電信所 博士生 (Robot Learning Lab)

17:00 - 18:00 論文分享 Session 3

1. Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
   蔡育哲，資工所 博士生 (Machine Intelligence and Agentic System Lab)

2. Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs 
   譚智睿，資工所 博士生 (Machine Intelligence & Understanding Laboratory)

3. Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors
   陳妍姍，資工所 碩士生 (Machine Intelligence & Understanding Laboratory)

4. Nipping the butterfly effect in the bud: Self-Output Fine Tuning for Autoregressive Weather Prediction
   蔡昀燁，資工所 碩士生 (Computational Learning Lab)