Foundation Models

ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts ICCV 2025 Protein2Text: Resampling Mechanism to Translate Protein Sequences into Human-Interpretable Text NAACL 2025 ProteinBench: A Holistic Evaluation of Protein Foundation Models ICLR 2025 Protein Language Model Fitness is a Matter of Preference ICLR 2025 Protein Large Language Models: A Comprehensive Survey EMNLP 2025 Protein Structure Tokenization: Benchmarking and New Recipe ICML 2025 PUMA: Empowering Unified MLLM with Multi-granular Visual Generation ICCV 2025 PunMemeCN: A Benchmark to Explore Vision-Language Models’ Understanding of Chinese Pun Memes EMNLP 2025 Putting People in LLMs’ Shoes: Generating Better Answers via Question Rewriter AAAI 2025 PwnGPT: Automatic Exploit Generation Based on Large Language Models ACL 2025 PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents AACL 2025 PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models ICML 2025 Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation ICLR 2025 QDTSynth: Quality-Driven Formal Theorem Synthesis for Enhancing Proving Performance of LLMs ACL 2025 QiMeng-GEMM: Automatically Generating High-Performance Matrix Multiplication Code by Exploiting Large Language Models AAAI 2025 QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach OSDI 2025 QiMP at SemEval-2025 Task 11: Optimizing Text-based Emotion Classification in English Beyond Traditional Methods SemEval 2025 QMamba: On First Exploration of Vision Mamba for Image Quality Assessment ICML 2025 Quantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language Models ACL 2025 Query-Driven Multimodal GraphRAG: Dynamic Local Knowledge Graph Construction for Online Reasoning ACL 2025 Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking EMNLP 2025 QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory EMNLP 2025 Racing Thoughts: Explaining Contextualization Errors in Large Language Models NAACL 2025 Radiant Foam: Real-Time Differentiable Ray Tracing ICCV 2025 Radiology Report Generation via Multi-objective Preference Optimization AAAI 2025