Machine Learning

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models ACL 2025 LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation ACL 2025 LongRoPE2: Near-Lossless LLM Context Window Scaling ICML 2025 Long-Sequence Recommendation Models Need Decoupled Embeddings ICLR 2025 Long-Short Decision Transformer: Bridging Global and Local Dependencies for Generalized Decision-Making ICLR 2025 LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains EMNLP 2025 Long-Tail Crisis in Nearest Neighbor Language Models NAACL 2025 Long-tailed Adversarial Training with Self-Distillation ICLR 2025 Long-Tailed Classification with Multi-Granularity Semantics ICCV 2025 Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail AAAI 2025 LongTail-Swap: benchmarking language models’ abilities on rare words EMNLP 2025 Long-Term Ad Memorability: Understanding & Generating Memorable Ads WACV 2025 Long-Term EEG Partitioning for Seizure Onset Detection AAAI 2025 Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning IJCAI 2025 Long-time asymptotics of noisy SVGD outside the population limit ICLR 2025 LongVILA: Scaling Long-Context Visual Language Models for Long Videos ICLR 2025 LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability EMNLP 2025 Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models EMNLP 2025 Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025 LookAlike: Consistent Distractor Generation in Math MCQs ACL 2025 Look Around Before Locating: Considering Content and Structure Information for Visual Grounding AAAI 2025 Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning AAAI 2025 Look Beyond Feeling: Unveiling Latent Needs from Implicit Expressions for Proactive Emotional Support EMNLP 2025 Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training ACL 2025