Artificial Intelligence

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025 Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness ICLR 2025 Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection UAI 2025 Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition ICCV 2025 Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix ICLR 2025 Beyond Linear Steering: Unified Multi-Attribute Control for Language Models EMNLP 2025 Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning CVPR 2025 Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs NAACL 2025 Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025 Beyond Mandatory Federations: Balancing Egoism, Utilitarianism and Egalitarianism in Mixed-Motive Games AAAI 2025 Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation ICML 2025 Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions IJCNLP 2025 Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks ICLR 2025 Beyond Message Passing: Neural Graph Pattern Machine ICML 2025 Beyond Metrics: Evaluating LLMs Effectiveness in Culturally Nuanced, Low-Resource Real-World Scenarios ACL 2025 Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification ICLR 2025 Beyond Monotonicity: On the Convergence of Learning Algorithms in Standard Auction Games AAAI 2025 Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents ACL 2025 Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs EMNLP 2025 Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models EMNLP 2025 Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning ACL 2025 Beyond Paraphrasing: Analyzing Summarization Abstractiveness and Reasoning EMNLP 2025 Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction IJCAI 2025 Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task ACL 2025 Beyond Pixel and Object: Part Feature as Reference for Few-Shot Video Object Segmentation AAAI 2025