Foundation Models

When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy EMNLP 2025 When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs EMNLP 2025 When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning EMNLP 2025 When to Speak, When to Abstain: Contrastive Decoding with Abstention ACL 2025 Which Word Orders Facilitate Length Generalization in LMs? An Investigation with GCG-Based Artificial Languages EMNLP 2025 Whole Genome Transformer for Gene Interaction Effects in Microbiome Habitat Specificity AAAI 2025 Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning EMNLP 2025 Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs ACL 2025 WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization CoNLL 2025 WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications ACL 2025 World Knowledge-Enhanced Reasoning Using Instruction-Guided Interactor in Autonomous Driving AAAI 2025 WorldScore: A Unified Evaluation Benchmark for World Generation ICCV 2025 Writing Like the Best: Exemplar-Based Expository Text Generation ACL 2025 xLAM: A Family of Large Action Models to Empower AI Agent Systems NAACL 2025 X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding EMNLP 2025 X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting ICCV 2025 YodiV3: NLP for Togolese Languages with Eyaa-Tom Dataset and the Lom Metric ACL 2025 You Only Use Reactive Attention Slice When Retrieving From Long Context EMNLP 2025 Z1: Efficient Test-time Scaling with Code EMNLP 2025 ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction EMNLP 2025 ZERA: Zero-init Instruction Evolving Refinement Agent – From Zero Instructions to Structured Prompts via Principle-based Optimization EMNLP 2025 Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency EMNLP 2025 Zero-Shot Belief: A Hard Problem for LLMs EMNLP 2025 Zero-Shot Detection of Out-of-Context Objects using Foundation Models WACV 2025 Zero-shot forecasting of chaotic systems ICLR 2025