news

Jan 26, 2026 Graph Tokenization for Bridging Graphs and Transformers is published in ICLR 2026.
Sep 18, 2025 Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models is published in NeurIPS 2025 (Spotlight).
Jan 23, 2025 MAP: Multi-Human-Value Alignment Palette is published in ICLR 2025 (Oral).
Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing is published in ICLR 2025.
Jan 23, 2025 AID: Adaptive Integration of Detectors for Safe AI with Language Models is published in NAACL 2025.