Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation
arXiv:2604.00477v1 Announce Type: new Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how many are needed? Through 960 sessions with two model pairs...
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
arXiv:2604.00012v1 Announce Type: cross Abstract: Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series, demonstrate strong reasoning...
PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction
arXiv:2604.01349v1 Announce Type: new Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation...
Robust Graph Representation Learning via Adaptive Spectral Contrast
arXiv:2604.01878v1 Announce Type: new Abstract: Spectral graph contrastive learning has emerged as a unified paradigm for handling both homophilic and heterophilic graphs by leveraging high-frequency components. However, we identify a fundamental spectral dilemma: while high-frequency signals are indispensable for encoding...
MSA-Thinker: Discrimination-Calibration Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis
arXiv:2604.00013v1 Announce Type: cross 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....
FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models
arXiv:2604.01762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has emerged as a crucial paradigm for adapting large language models (LLMs) under constrained computational budgets. However, standard PEFT methods often struggle in multi-task fine-tuning settings, where diverse optimization objectives induce task...
Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
arXiv:2604.00445v1 Announce Type: new Abstract: Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance across configurations, which significantly limits their applicability. In this work, we...
Dual-Attention Based 3D Channel Estimation
arXiv:2604.01769v1 Announce Type: new Abstract: For multi-input and multi-output (MIMO) channels, the optimal channel estimation (CE) based on linear minimum mean square error (LMMSE) requires three-dimensional (3D) filtering. However, the complexity is often prohibitive due to large matrix dimensions. Suboptimal...
Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries
arXiv:2604.00228v1 Announce Type: new Abstract: Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal behavior,...
Amazon is trying to buy Globalstar to compete with SpaceX's Starlink
Amazon wants in on the low-Earth orbit Internet action.
SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
arXiv:2604.01337v1 Announce Type: new Abstract: While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high performance, exhibit significant instability...
Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager
arXiv:2604.00011v1 Announce Type: cross Abstract: The growing prominence of large language models (LLMs) in daily life has heightened concerns that LLMs exhibit many of the same gender-related biases as their creators. In the context of hiring decisions, we quantify the...
"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems
arXiv:2604.00026v1 Announce Type: new Abstract: When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous...
Bridging Deep Learning and Integer Linear Programming: A Predictive-to-Prescriptive Framework for Supply Chain Analytics
arXiv:2604.01775v1 Announce Type: new Abstract: Although demand forecasting is a critical component of supply chain planning, actual retail data can exhibit irreconcilable seasonality, irregular spikes, and noise, rendering precise projections nearly unattainable. This paper proposes a three-step analytical framework that...
Frege in the Flesh: Biolinguistics and the Neural Enforcement of Syntactic Structures
arXiv:2604.00291v1 Announce Type: new Abstract: Biolinguistics is the interdisciplinary scientific study of the biological foundations, evolution, and genetic basis of human language. It treats language as an innate biological organ or faculty of the mind, rather than a cultural tool,...
Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
arXiv:2604.00547v1 Announce Type: new Abstract: Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a single architecture. While this architectural unification, driven by the deep fusion of multimodal features, enhances model performance, it also introduces important yet underexplored...
A Retrospective on the ICLR 2026 Review Process
Pseudo-Quantized Actor-Critic Algorithm for Robustness to Noisy Temporal Difference Error
arXiv:2604.01613v1 Announce Type: new Abstract: In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and...
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
arXiv:2604.00004v1 Announce Type: cross Abstract: The extension of context windows in Large Language Models is typically facilitated by scaling positional encodings followed by lightweight Continual Pre-Training (CPT). While effective for processing long sequences, this paradigm often disrupts original model capabilities,...
Training In-Context and In-Weights Mixtures Via Contrastive Context Sampling
arXiv:2604.01601v1 Announce Type: new Abstract: We investigate training strategies that co-develop in-context learning (ICL) and in-weights learning (IWL), and the ability to switch between them based on context relevance. Although current LLMs exhibit both modes, standard task-specific fine-tuning often erodes...
LLM Essay Scoring Under Holistic and Analytic Rubrics: Prompt Effects and Bias
arXiv:2604.00259v1 Announce Type: new Abstract: Despite growing interest in using Large Language Models (LLMs) for educational assessment, it remains unclear how closely they align with human scoring. We present a systematic evaluation of instruction-tuned LLMs across three open essay-scoring datasets...
Improving Latent Generalization Using Test-time Compute
arXiv:2604.01430v1 Announce Type: new Abstract: Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary strengths, in-weights learning frequently struggles to...
Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning
arXiv:2604.01345v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) recovers the loss function of a forward learner from its observed responses adaptive IRL aims to reconstruct the loss function of a forward learner by passively observing its gradients as it...
Koopman-Based Nonlinear Identification and Adaptive Control of a Turbofan Engine
arXiv:2604.01730v1 Announce Type: new Abstract: This paper investigates Koopman operator-based approaches for multivariable control of a two-spool turbofan engine. A physics-based component-level model is developed to generate training data and validate the controllers. A meta-heuristic extended dynamic mode decomposition is...
More Human, More Efficient: Aligning Annotations with Quantized SLMs
arXiv:2604.00586v1 Announce Type: new Abstract: As Large Language Model (LLM) capabilities advance, the demand for high-quality annotation of exponentially increasing text corpora has outpaced human capacity, leading to the widespread adoption of LLMs in automatic evaluation and annotation. However, proprietary...
The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
arXiv:2604.00478v2 Announce Type: new Abstract: Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and adjusts AI behavior...
Authors' lucky break in court may help class action over Meta torrenting
Judge gave authors an easier attack on Meta’s torrenting. Meta hopes SCOTUS ruling will block it.
Signals: Trajectory Sampling and Triage for Agentic Interactions
arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such systems are now deployed at scale, improving them post-deployment remains challenging. Agent trajectories...
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
arXiv:2604.00375v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregressive (AR) LLMs. In practice, however, random-order decoding often hurts generation quality....
Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models
arXiv:2604.01622v1 Announce Type: new Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation. We show that expert-choice (EC)...