Interpretability

The Future Is Neuro-Symbolic: Where Has It Been, and Where Is It Going? AAAI 2026 The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models ACL 2026 The Other Mind: How Language Models Exhibit Human Temporal Cognition AAAI 2026 The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs WACV 2026 The Shape of Vulnerability: How Adversarial Perturbations Reshape the Topology of Language Model Latent Spaces ACL 2026 Thesis proposal: COGNILENS: Analyzing Cognitive Decline in Language Models for Alzheimer’s Monitoring EACL 2026 Thesis Proposal: Comparing Human and Model Perception of Writing Style under Controlled Perturbations EACL 2026 Thinking beyond the anthropomorphic paradigm benefits LLM research ACL 2026 Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model CVPR 2026 Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification AAAI 2026 Topology-aware Knowledge Preservation for Class-Incremental Learning AAAI 2026 Toward Controllable and Trustworthy LLM Reasoning: From Failure Mapping to Cognition-inspired Control and Real-world Impact AAAI 2026 Towards Inclusive Communication in Cancer Prevention and Treatment: A Case Study on Italian Informational Materials EACL 2026 Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph ACL 2026 Towards Intrinsic Interpretability of Large Language Models: A Survey of Design Principles and Architectures ACL 2026 Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood WACV 2026 Towards Trustworthy Multimodal AI Systems AAAI 2026 Towards Ultrasound-based Reliable Disease Diagnosis Using Causal Inference AAAI 2026 TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG ACL 2026 TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models EACL 2026 Trajectory Signatures of Deception in Large Language Models ACL 2026 Transparent Networks for Multivariate Time Series AAAI 2026 TRANSPORTER: Transferring Visual Semantics from VLM Manifolds CVPR 2026 TrustTable: A Neuro-Symbolic Auditing Framework for Faithful Table QA ACL 2026 Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable Code AAAI 2026