Search AI News
Find articles across all categories and topics
82 results for "interpretability"
Missing No More: Dictionary-Guided Cross-Modal Image Fusion under Missing Infrared
arXiv:2603.08018v2 Announce Type: replace Abstract: Infrared-visible (IR-VIS) image fusion is vital for perception and security, yet most methods rely on the availability of both modalities during training and inference. When the infrared modality is absent, pixel-space generative substitutes become hard to control and inherently lack interpretability. We address missing-IR fusion by proposing a dictionary-guided, coefficient-domain framework built upon a shared convolutional dictionary. The pipeline comprises three key components: (1) Joint Shared-dictionary Representation Learning (JSRL) lea — Yafei Zhang, Meng Ma, Huafeng Li, Yu Liu
From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability
arXiv:2603.29805v2 Announce Type: replace-cross Abstract: A key problem in the modern study of AI is predicting and understanding emergent capabilities in models during training. Inspired by methods for studying reactions in quantum chemistry, we present the ``2-datapoint reduced density matrix". We show that this object provides a computationally efficient, unified observable of phase transitions during training. By tracking the eigenvalue statistics of the 2RDM over a sliding window, we derive two complementary signals: the spectral heat capacity, which we prove provides early warning of sec — Max Hennick, Guillaume Corlouer
CodeDance: A Dynamic Tool-integrated MLLM for Executable Visual Reasoning
arXiv:2512.17312v2 Announce Type: replace Abstract: Recent releases such as o3 highlight human-like "thinking with images" reasoning that combines tool use with stepwise verification, yet most open-source approaches still rely on text-only chains, rigid visual schemas, or single-step pipelines, limiting flexibility, interpretability, and transferability on complex tasks. We introduce CodeDance, which explores executable code as a general solver for visual reasoning. Unlike fixed-schema calls (e.g., only predicting bounding-box coordinates), CodeDance defines, composes, and executes code to orc — Qi Song, Honglin Li, Yingchen Yu, Haoyi Zhou, Lin Yang, Song Bai, Qi She, Zilong Huang, Yunqing Zhao
DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
arXiv:2603.24587v2 Announce Type: replace Abstract: We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual interpretability. Training RL policies on real-world driving data incurs prohibitive costs and safety risks. While existing pixel-level diffusion world models enable safe imagination-based training, they suffer from multi-step diffusion inference latency (2s/frame) that prevents high-frequency RL interaction. Ou — Pengxuan Yang, Yupeng Zheng, Deheng Qian, Zebin Xing, Qichao Zhang, Linbo Wang, Yichen Zhang, Shaoyu Guo, Zhongpu Xia, Qiang Chen, Junyu Han, Lingyun Xu, Yifeng Pan, Dongbin Zhao
Closing the Confidence-Faithfulness Gap in Large Language Models
arXiv:2603.25052v2 Announce Type: replace-cross Abstract: Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic interpretability analysis of verbalized confidence, using linear probes and contrastive activation addition (CAA) steering to show that calibration and verbalized confidence signals are encoded linearly but are orthogonal to one another -- a finding consistent across three open-weight models and four d — Miranda Muqing Miao, Lyle Ungar
Detecting Multi-Agent Collusion Through Multi-Agent Interpretability
arXiv:2604.01151v1 Announce Type: cross Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting deception in single-agent settings, collusion is inherently a multi-agent phenomenon, and the use of internal representations for detecting collusion between agents remains unexplored. We introduce NARCBench, a benchmark for evaluating collusion detection under environment distribution shift, and propose five probing techniques that aggregate per-agent deception scores to classify scenarios at the group level. Our probes achieve 1.00 AUROC in-distribution and 0.60--0.86 AUROC when transferred zero-shot to structu
Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis
arXiv:2603.17624v2 Announce Type: replace Abstract: Understanding whether large language models (LLMs) capture structured meaning requires examining how they represent concept relationships. In this work, we study three models of increasing scale: Pythia-70M, GPT-2, and Llama 3.1 8B, focusing on four semantic relations: synonymy, antonymy, hypernymy, and hyponymy. We combine linear probing with mechanistic interpretability techniques, including sparse autoencoders (SAE) and activation patching, to identify where these relations are encoded and how specific features contribute to their represen — Andor Diera, Ansgar Scherp
Tracking Equivalent Mechanistic Interpretations Across Neural Networks
arXiv:2603.30002v1 Announce Type: cross Abstract: Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that task. However, MI is difficult to scale and generalize. This stems in part from two key challenges: there is no precise notion of a valid interpretation; and, generating interpretations is often an ad hoc process. In this paper, we address these challenges by defining and studying the problem of interpretive e — Alan Sun, Mariya Toneva
Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex Trading
arXiv:2604.00031v1 Announce Type: cross Abstract: Applying reinforcement learning (RL) to foreign exchange (Forex) trading remains challenging because realistic environments, well-defined reward functions, and expressive action spaces must be satisfied simultaneously, yet many prior studies rely on simplified simulators, single scalar rewards, and restricted action representations, limiting both interpretability and practical relevance. This paper presents a modular RL framework designed to address these limitations through three tightly integrated components: a friction-aware execution engine — Nabeel Ahmad Saidd
Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations
arXiv:2604.00599v1 Announce Type: new Abstract: Predicting the behavior of ultra-large complex systems, from climate to biological and technological networks, is a central unsolved challenge. Existing approaches face a fundamental trade-off: equation discovery methods provide interpretability but fail to scale, while neural networks scale but operate as black boxes and often lose reliability over long times. Here, we introduce the Sparse Identification Graph Neural Network, a framework that overcome this divide by allowing to infer the governing equations of large networked systems from data. — Qi Shao, Duxin Chen, Jiawen Chen, Yujie Zeng, Athen Ma, Wenwu Yu, Vito Latora, Wei Lin
MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
arXiv:2506.18919v4 Announce Type: replace-cross Abstract: As a multimodal medium combining images and text, memes frequently convey implicit harmful content through metaphors and humor, rendering the detection of harmful memes a complex and challenging task. Although recent studies have made progress in detection accuracy and interpretability, large-scale, high-quality datasets for harmful memes remain scarce, and current methods still struggle to capture implicit risks and nuanced semantics. Thus, we construct MemeMind, a large-scale harmful meme dataset. Aligned with the international standa — Hexiang Gu, Qifan Yu, Yuan Liu, Zikang Li, Saihui Hou, Jian Zhao, Zhaofeng He
Explainable AI for Blind and Low-Vision Users: Navigating Trust, Modality, and Interpretability in the Agentic Era
arXiv:2604.00187v1 Announce Type: cross Abstract: Explainable Artificial Intelligence (XAI) is critical for ensuring trust and accountability, yet its development remains predominantly visual. For blind and low-vision (BLV) users, the lack of accessible explanations creates a fundamental barrier to the independent use of AI-driven assistive technologies. This problem intensifies as AI systems shift from single-query tools into autonomous agents that take multi-step actions and make consequential decisions across extended task horizons, where a single undetected error can propagate irreversibly — Abu Noman Md Sakib, Protik Dey, Zijie Zhang, Taslima Akter
MSA-Thinker: Discrimination-Calibration Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
arXiv:2604.00013v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to understand human emotions by integrating textual, auditory, and visual modalities. Although Multimodal Large Language Models (MLLMs) have achieved state-of-the-art performance via supervised fine-tuning (SFT), their end-to-end "black-box" nature limits interpretability. Existing methods incorporating Chain-of-Thought (CoT) reasoning are hindered by high annotation costs, while Reinforcement Learning (RL) faces challenges such as low exploration efficiency and sparse rewards, particularly on hard samples. To address these issues, we propose a novel training framework that integrates structured Discrimination-Calibration (DC) reasoning with Hint-based Reinforcement Learning. First, we perform cold-start SFT
Epileptic Seizure Detection in Separate Frequency Bands Using Feature Analysis and Graph Convolutional Neural Network (GCN) from Electroencephalogram (EEG) Signals
arXiv:2604.00163v1 Announce Type: cross Abstract: Epileptic seizures are neurological disorders characterized by abnormal and excessive electrical activity in the brain, resulting in recurrent seizure events. Electroencephalogram (EEG) signals are widely used for seizure diagnosis due to their ability to capture temporal and spatial neural dynamics. While recent deep learning methods have achieved high detection accuracy, they often lack interpretability and neurophysiological relevance. This study presents a frequency-aware framework for epileptic seizure detection based on ictal-phase EEG analysis. The raw EEG signals are decomposed into five frequency bands (delta, theta, alpha, lower beta, and higher beta), and eleven discriminative features are extracted from each band. A graph convol
STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
arXiv:2602.14265v2 Announce Type: replace Abstract: Inference-Time-Compute (ITC) methods like Best-of-N and Tree-of-Thoughts are meant to produce output candidates that are both high-quality and diverse, but their use of high-temperature sampling often fails to achieve meaningful output diversity. Moreover, existing ITC methods offer limited control over how to perform reasoning, which in turn limits their interpretability. We present STATe Of Thoughts (STATe), an interpretable ITC method that searches over high-level reasoning patterns. STATe replaces stochastic sampling with discrete and int — Zachary Bamberger, Till R. Saenger, Gilad Morad, Ofra Amir, Brandon M. Stewart, Amir Feder
Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
arXiv:2507.17851v3 Announce Type: replace-cross Abstract: Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks through supposedly anonymized representations. We present two contributions to address these challenges. First, we develop InterpTRQE-SptME (Timbre Residual Quantitative Evaluation Benchmark of Speech pre-training Models Encoding via Interpretability), a benchmark that directly measures residual speaker information in content embeddings using SHAP-based interpretability analysis. Unlike existing indirect metrics, our approach quantifies the exact proportion of speaker information remaining after dis