Search: “research”

Lifted Schrodinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions

arXiv:2605.24795v1 Announce Type: cross Abstract: We study stochastic density control between Gaussian-mixture endpoint distributions under Brownian prior dynamics. Since the direct Schrodinger bridge

Research

LLM-SAA: LLM-persona Generated Distributions for Decision-making

DGX agent

arXiv:2602.06357v2 Announce Type: replace Abstract: LLMs can generate a wealth of data, ranging from simulated personas imitating human valuations and preferences, to demand forecasts based on world k

researcharxiv-cs-lg

26 May 2026

LLMs Show No Signs Of Individuated Metacognition

arXiv:2605.24299v1 Announce Type: new Abstract: Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capabilit

Logic-Guided Socially-aware Robot Navigation World Model

arXiv:2510.23509v2 Announce Type: replace Abstract: Social robot navigation increasingly relies on large language models for reasoning, path planning, and enabling movement in dynamic human spaces. Ho

Logic-Guided Vector Fields for Constrained Generative Modeling

arXiv:2602.02009v2 Announce Type: replace Abstract: Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typ

Loosely Coupled Factor Graph Optimization for Pseudolite-Augmented Navigation

arXiv:2605.24980v1 Announce Type: new Abstract: In Global Navigation Satellite System (GNSS)-degraded environments, pseudolites (PLs) provide additional signal sources to enhance positioning performan

Low-Cost Labels, Reliable Choices: Rollout-Calibrated Hyper-Heuristics for Job Shop Scheduling

arXiv:2605.23957v1 Announce Type: new Abstract: Learning-assisted hyper-heuristics can select among dispatching rules while preserving the feasibility and interpretability of constructive Job Shop Sch

LRDDv3: High-Resolution Long-Range Drone Detection Dataset with Range Information and Thermal Data

arXiv:2605.25942v1 Announce Type: cross Abstract: Unmanned Aerial Vehicles (UAVs) have quickly become common in various airspaces, representing a wide range of applications from recreation flying to c

Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments

arXiv:2605.24020v1 Announce Type: cross Abstract: Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia query

Machine Learning Multiscale Interactions

arXiv:2605.25710v1 Announce Type: cross Abstract: Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predi

Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training

arXiv:2605.25966v1 Announce Type: cross Abstract: We test whether the optimal learning-rate schedule depends on bit-width during from-initialisation quantisation-aware training (QAT) for sub-100M deco

MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training

arXiv:2605.25771v1 Announce Type: cross Abstract: Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, ex

MEMOR-E: In-Context and Fine-Tuned LLM Personalization for Alzheimer's Assistive Robotics

arXiv:2605.23941v1 Announce Type: new Abstract: Alzheimer's disease is a neurodegenerative disorder marked by progressive declines in memory and language that reduce independence in daily life, motiva

Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data

arXiv:2605.25004v1 Announce Type: cross Abstract: Inferring network-wide traffic states from sparse observations with high accuracy and trustworthy uncertainty quantification is essential for intellig

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization

arXiv:2605.24019v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited reso

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing

arXiv:2605.24973v1 Announce Type: cross Abstract: VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within

Mitigating Gradient Pathology in PINNs through Aligned Constraint

arXiv:2605.25001v1 Announce Type: new Abstract: While Physics-Informed Neural Networks (PINNs) are powerful for solving Partial Differential Equations (PDEs), their training is often paralyzed by grad

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration

arXiv:2605.24957v1 Announce Type: new Abstract: The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (L

Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation

arXiv:2605.25869v1 Announce Type: new Abstract: Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unc

Mixture of Complementary Agents for Robust LLM Ensemble

arXiv:2605.24048v1 Announce Type: cross Abstract: Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising paradigm for aggregating information and boosting

MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM

arXiv:2602.20191v2 Announce Type: replace-cross Abstract: Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with v

Momentum Streams for Optimizer-Inspired Transformers

arXiv:2605.24425v1 Announce Type: cross Abstract: The residual update of a pre-norm Transformer layer admits an interpretation as one step of a first-order optimizer acting on a surrogate token energy

Multilingual Phonological Feature Recognition with Self-Supervised Speech Models

arXiv:2605.25596v1 Announce Type: new Abstract: Phonological features provide a language-general and linguistically grounded representation of speech. We present PhonoQ-2.0, a multilingual frame-level

Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra

arXiv:2605.24770v1 Announce Type: new Abstract: Muon is a recently developed matrix-aware optimizer that has shown strong results in transformer training, but its behavior in vision transformers (ViTs

Musician and human rights activist Peter Gabriel sent a special congratulatory message to Brewster Kahle, founder and digital librarian of t…

Musician and human rights activist Peter Gabriel sent a special congratulatory message to Brewster Kahle, founder and digital librarian of the Internet Archive, on being honored as a 2026 Computer His

researchyann-lecun--x

MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation

arXiv:2605.24914v1 Announce Type: cross Abstract: To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely

Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles

arXiv:2306.14853v5 Announce Type: replace-cross Abstract: In this work, we consider bilevel optimization when the lower-level problem is strongly convex. Recent works show that with a Hessian-vector p

NEST: Network- and Memory-Aware Device Placement For Distributed Deep Learning

arXiv:2603.06798v2 Announce Type: replace Abstract: The growing scale of deep learning demands distributed training frameworks that jointly reason about parallelism, memory, and network topology. Prio

Neural Stochastic Differential Equations on Compact State Spaces: Theory, Methods, and Application to Suicide Risk Modeling

arXiv:2508.17090v4 Announce Type: replace-cross Abstract: Ecological Momentary Assessment (EMA) studies enable the collection of high-frequency self-reports of suicidal thoughts and behaviors (STBs) v

NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding

arXiv:2605.24993v1 Announce Type: new Abstract: Current fMRI decoders face a performance-fidelity trade-off where efficient ID encoders outperform geometrically faithful surface-based models. We argue

NITP: Next Implicit Token Prediction for LLM Pre-training

arXiv:2605.24956v1 Announce Type: new Abstract: Standard next-token prediction (NTP) supervises language models solely through discrete labels in the output logit space. We argue that this sparse one-

NPSolver: Neural Poisson Solver with Iterative Physics Supervision

arXiv:2605.25786v1 Announce Type: cross Abstract: Efficiently solving Poisson equations on complex, irregular domains remains a fundamental challenge in scientific computing, as classical iterative so

Nystrom Kernel Stein Discrepancy Tests

arXiv:2605.25173v1 Announce Type: cross Abstract: Kernel Stein discrepancy (KSD) is among the most popular goodness-of-fit (GoF) measures on general domains with a large number of successful deploymen

On the Interaction of Batch Noise, Adaptivity, and Compression, under (L_0,L_1)-Smoothness: An SDE Approach

arXiv:2506.00181v2 Announce Type: replace Abstract: Distributed stochastic optimization intertwines (i) stochastic gradient noise, (ii) communication compression, and (iii) adaptive/normalized updates

On the Limits of Model Merging for Multilinguality in Pre-Training

arXiv:2605.25846v1 Announce Type: new Abstract: Endowing models with consistent multilingual performance can be achieved by mixing pre-training data, or post-training approaches such as language-speci

One-shot Conditional Sampling: MMD meets Nearest Neighbors

arXiv:2509.25507v2 Announce Type: replace-cross Abstract: How can we generate samples from a conditional distribution that we never fully observe? This question arises across a broad range of applicat

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

arXiv:2605.25663v1 Announce Type: new Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space wit

Optimal Non-Asymptotic Edgeworth Expansions for Multivariate Neural Network Outputs

arXiv:2605.24072v1 Announce Type: cross Abstract: Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanish

Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function

arXiv:2603.16481v2 Announce Type: replace Abstract: Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler fo

P1SCO: Social Dimensions from a Perspectivist Lens

arXiv:2605.25312v1 Announce Type: new Abstract: We introduce P1SCO, a dataset of social media comments collected from three distinct platforms, annotated according to ten social dimensions to capture

PAC Learning with Bandit Feedback: Sharp Sample Complexity in the Realizable Setting

arXiv:2605.25678v1 Announce Type: cross Abstract: We study the problem of multiclass PAC learning with bandit feedback in the realizable setting. In this framework, there is an unknown data distributi

PACT: Proactive Asking for Continual Task Assistance in Human-Robot Collaboration

arXiv:2605.24350v1 Announce Type: new Abstract: Robotic assistants in long-term human-robot collaboration need to assist users under partial observations while leveraging cross-day interaction history

PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models

arXiv:2512.20063v3 Announce Type: replace Abstract: We introduce exttt{PairFlow}, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiri

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

arXiv:2605.10977v2 Announce Type: replace-cross Abstract: Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. Ho

PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs

arXiv:2603.09943v2 Announce Type: replace Abstract: Computational pathology demands both visual pattern recognition and dynamic integration of structured domain knowledge, including taxonomy, grading

Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions

arXiv:2605.24621v1 Announce Type: cross Abstract: Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in

{Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation

arXiv:2605.24509v1 Announce Type: cross Abstract: Latent video diffusion models generate videos by progressively transforming Gaussian noise into realistic samples conditioned on text or visual inputs

Phonetic Modeling of Dialectal Variation in Vietnamese Speech

arXiv:2605.24451v1 Announce Type: new Abstract: Vietnamese exhibits substantial dialectal phonetic variation across Northern, Central, and Southern regions, where identical lexical items may be realiz