Multi-Block Diffusion Language Models
Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation. A natural next step is to extend them from Single-Block Diffusion…
Papers 5330 stories
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key…
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive
Generative models have achieved remarkable progress, yet applying them to satellite imagery remains challenging. Unlike natural imagery, satellite scenes are structured by spatially complex and semantically…
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with…
BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
Modeling the bidirectional correspondence between external sensory stimuli and internal neural activity has emerged as a critical frontier in neuroscience. However, existing approaches predominantly treat brain…
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless…
A Technical Typology of AI Systems in Public Administration
arXiv:2606.31755v1 Announce Type: cross Abstract: Research on artificial intelligence (AI) in the public sector often treats "AI" as a single category, neglecting technical distinctions between different…
Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment
arXiv:2606.30953v1 Announce Type: new Abstract: We introduce the Neuro-Bayesian-Symbolic Residual Attention Shallow Network (NBS-RASN), a hybrid neural architecture for explainable cybersecurity risk assessment in open-source ecosystems.…
Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning
arXiv:2606.30857v1 Announce Type: new Abstract: This paper describes our submission to SemEval-2026 Task 9 on detecting multilingual, multicultural, and multievent online polarization. We address all three…
Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk
arXiv:2604.18546v2 Announce Type: replace Abstract: We propose a distributionally robust approach to risk-sensitive estimation of an unknown signal x from an observed signal y. The observation…
Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization
arXiv:2606.30836v1 Announce Type: new Abstract: Explainability in Many-Objective Optimization (MaO) is currently hindered by the escalating complexity of the Pareto front, which renders the relationship between…
A Large-Scale Empirical Evaluation of MMAO Under Fair-Budget Continuous and Discrete Benchmarks
arXiv:2606.31584v1 Announce Type: new Abstract: This paper evaluates the Metabolic Multi-Agent Optimizer (MMAO) under a stricter empirical protocol rather than reintroducing the framework itself. The study…
Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Product of Random Matrices
arXiv:2606.30831v1 Announce Type: cross Abstract: We study the squared singular value spectrum of a product of non-square random matrices, a setting that also corresponds to the…
Amplifying Membership Signal Through Chained Regeneration
arXiv:2606.31991v1 Announce Type: cross Abstract: The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. Current…
DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks
arXiv:2602.03981v2 Announce Type: replace-cross Abstract: Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock…
When transformers learn "impossible" languages, what do they learn?
arXiv:2606.30815v1 Announce Type: new Abstract: Recent work suggests that transformer language models show a bias towards human languages over unnatural ("impossible") languages argued to be unacquirable…
A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection
arXiv:2606.10410v2 Announce Type: replace Abstract: Objective: Accurate classification of physiological signals in real-world deployments is challenged by sensor noise, motion artifacts, and distribution shifts between training…
Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors
arXiv:2606.31845v1 Announce Type: cross Abstract: A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes. In a parameter-neutral…
Criticality-Constrained Iterative Pruning for Energy-Efficient Spiking Neural Networks via Combined Importance Scoring
arXiv:2606.30676v1 Announce Type: new Abstract: Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity. Existing strategies either neglect…
On Variance Reduction in Learning Mean Flows
arXiv:2605.09235v2 Announce Type: replace-cross Abstract: One-step generative modeling has emerged as a leading approach for amortizing the inference cost of diffusion and flow-matching models. Among distillation-free…
Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking
arXiv:2606.29088v2 Announce Type: replace-cross Abstract: There are various benchmarks to evaluate bugfixing capabilities of Large Language Models. However, most widespread benchmarks do not fully reflect real-world…
HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
arXiv:2606.30966v1 Announce Type: new Abstract: Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor;…
When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
arXiv:2606.30814v1 Announce Type: new Abstract: Calibration evaluates whether a model confidence aligns with its empirical accuracy. Existing studies often compare the calibration of different large language…
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
arXiv:2509.10406v4 Announce Type: replace Abstract: Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs. We present Multipole…