{"total":171,"rows":[{"id":"2504.02732","title":"Why do LLMs attend to the first token?","created":"2025-04-03","cited_by_count":127,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2510.06477","title":"Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin","created":"2025-10-07","cited_by_count":52,"area":null},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2502.15637","title":"Mantis: Lightweight Foundation Model for Time Series Classification","created":"2025-02-21","cited_by_count":24,"area":null},{"id":"2505.18132","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models","created":"2025-05-23","cited_by_count":20,"area":null},{"id":"2509.03888","title":"False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize","created":"2025-09-04","cited_by_count":19,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2510.05092","title":"Learning to Interpret Weight Differences in Language Models","created":"2025-10-06","cited_by_count":11,"area":null},{"id":"2602.17868","title":"MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2605.06510","title":"Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2507.17394","title":"HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2511.20315","title":"Geometry of Decision Making in Language Models","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2601.22364","title":"Context Structure Reshapes the Representational Geometry of Language Models","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2505.17101","title":"A quantitative analysis of semantic information in deep representations of text and images","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2607.15178","title":"T^2MLR: Transformer with Temporal Middle-Layer Recurrence","created":"2026-07-16","cited_by_count":7,"area":null},{"id":"2502.10871","title":"Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs","created":"2025-02-15","cited_by_count":6,"area":null},{"id":"2502.16570","title":"Entropy-Lens: Uncovering Decision Strategies in LLMs","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2508.17734","title":"Layerwise Importance Analysis of Feed-Forward Networks in Transformer-based Language Models","created":"2025-08-25","cited_by_count":6,"area":null},{"id":"2509.23782","title":"Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2601.06851","title":"A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning","created":"2026-01-11","cited_by_count":6,"area":null},{"id":"2505.17099","title":"Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.00344","title":"Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs","created":"2025-05-31","cited_by_count":5,"area":null},{"id":"2506.02132","title":"Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2508.14067","title":"Punctuation and Predicates in Language Models","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2603.12451","title":"Overcoming the Modality Gap in Context-Aided Forecasting","created":"2026-03-12","cited_by_count":5,"area":null},{"id":"2503.10515","title":"Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set","created":"2025-03-13","cited_by_count":4,"area":null},{"id":"2506.06443","title":"Superior Molecular Representations from Intermediate Encoder Layers","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2601.09322","title":"Attentive multilayer fusion for vision transformers","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2603.04426","title":"Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2604.16902","title":"Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2606.03483","title":"Analyzing Stream Collapse in Hyper-Connections: From Diagnosis to Mitigation","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2502.19078","title":"Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2505.17998","title":"TRACE for Tracking the Emergence of Semantic Representations in Transformers","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2507.04404","title":"LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2508.18387","title":"Integral Transformer: Denoising Attention, Not Too Much Not Too Little","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2509.16660","title":"Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.06640","title":"Contextual Representation Flow Across Depth in State-Space and Transformer Architectures","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.08389","title":"Revisiting Hallucination Detection with Effective Rank-based Uncertainty","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2511.06516","title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2511.14868","title":"Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2512.24560","title":"Localized Calibrated Uncertainty in Code Language Models","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2601.10398","title":"LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2602.00767","title":"BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2602.01572","title":"LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.05988","title":"Layer-wise LoRA fine-tuning: a similarity metric approach","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.10448","title":"Instruction Data Selection via Answer Divergence","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2604.14128","title":"Rhetorical Questions in LLM Representations: A Linear Probing Study","created":"2026-04-15","cited_by_count":3,"area":null},{"id":"2605.00226","title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2605.09430","title":"FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2605.09969","title":"The Truth Lies Somewhere in the Middle (of the Generated Tokens)","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.23033","title":"Uncovering the Latent Potential of Deep Intermediate Representations","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2605.26366","title":"Automatic Layer Selection for Hallucination Detection","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2505.17793","title":"Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.17748","title":"HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2507.05387","title":"The Generalization Ridge: Information Flow in Natural Language Generation","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2509.06518","title":"Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2510.26025","title":"Exploring Human-AI Conceptual Alignment through the Prism of Chess","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2601.03798","title":"Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.04019","title":"Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.04081","title":"Abstraction Induces the Brain Alignment of Language and Speech Models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.21750","title":"From Words to Amino Acids: Does the Curse of Depth Persist?","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.01590","title":"IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshu","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.01822","title":"Emerging Human-like Strategies for Semantic Memory Foraging in Large Language Models","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.01834","title":"Probing Materials Knowledge in LLMs: From Latent Embeddings to Reliable Predictions","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.05280","title":"Layer by layer, module by module: Choose both for optimal OOD probing of ViT","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.08747","title":"Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.08260","title":"Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2604.13846","title":"Beyond Static Personas: Situational Personality Steering for Large Language Models","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2604.15706","title":"Target-Oriented Pretraining Data Selection via Neuron-Activated Graph","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2605.15393","title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.17084","title":"Scale Determines Whether Language Models Organize Representation Geometry for Prediction","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2605.29782","title":"Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.23670","title":"Tapered Language Models","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2606.26379","title":"Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2505.08727","title":"Memorization-Compression Cycles Improve Generalization","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2505.15504","title":"Exploiting Low-Dimensional Manifold of Features for Few-Shot Whole Slide Image Classification","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.00102","title":"ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Models","created":"2025-08-27","cited_by_count":1,"area":null},{"id":"2509.12650","title":"Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detection","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2509.25260","title":"Internal Planning in Language Models: Characterizing Horizon and Branch Awareness","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2512.13109","title":"Uncovering the Role of Initial Saliency in U-Shaped Attention Bias: Scaling Initial Token Weight for Enhanced Long-Text Processing","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2512.22944","title":"Multiple Token Divergence: Measuring and Steering In-Context Computation Density","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2601.16354","title":"NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2603.22665","title":"Improving LLM Final Representations with Inter-Layer Geometry","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.12714","title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.27970","title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.29850","title":"MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding","created":"2026-05-28","cited_by_count":1,"area":null}],"next_cursor":"100"}