Search: “research”

Fine-Tuning Improves Information Conveyance in Language Models

arXiv:2605.30844v1 Announce Type: cross Abstract: Fine-tuning is often believed to reduce uncertainty and diversity in large language models, but existing analyses overlook output length, a key confou

Fixed Universal Transformers

arXiv:2605.31423v1 Announce Type: new Abstract: We introduce universal transformers: fixed transformers that can simulate any transformer in a given class via a suitable input embedding. Analogous to

researcharxiv-cs-lg

1 Jun 2026

FlagGAM: Rule-Based Generalized Additive Modeling for Explainable Tabular Prediction

arXiv:2605.31189v1 Announce Type: new Abstract: Tabular prediction in high-stakes domains requires models that are accurate, transparent, and robust to imperfect inputs. We propose FlagGAM, a rule-def

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

arXiv:2601.01075v2 Announce Type: replace-cross Abstract: Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-moti

Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error

arXiv:2605.31438v1 Announce Type: new Abstract: Time series forecasting often requires learning nonlinear and time-delayed dependencies. A paradigmatic class of forecasting models are nonlinear vector

FLOWR: Flow Matching for Structure-Aware De Novo, Interaction- and Fragment-Based Ligand Generation

arXiv:2504.10564v3 Announce Type: replace-cross Abstract: We introduce FLOWR, a novel structure-based framework for the generation and optimization of three-dimensional ligands. FLOWR integrates conti

Formalizing and falsifying causal pathways of rare events

arXiv:2605.31254v1 Announce Type: new Abstract: Building on recent formalizations of root cause analysis for rare events (``outliers'') in structural equation models, we propose a formal definition of

Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation

arXiv:2605.30893v1 Announce Type: new Abstract: Variational autoencoders (VAEs) compress high resolution CT volumes into compact latents while preserving clinically relevant structure. However, traini

Fraud Type Decomposition and the Observation-Mechanism Taxonomy:Class-Specific Detection Limits in Payment Networks

arXiv:2605.31257v1 Announce Type: new Abstract: Fraud detection in payment networks relies on labels generated through heterogeneous and imperfect observation processes, yet existing approaches treat

Free energy Estimation on Any State Space

arXiv:2605.31063v1 Announce Type: cross Abstract: Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformation

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

arXiv:2602.24210v2 Announce Type: replace-cross Abstract: Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to c

From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift

arXiv:2605.31187v1 Announce Type: new Abstract: Detecting covariate shift is critical for building reliable vision systems. While most prior work focuses on improving robustness to shift, explicitly d

From Mean-Field Limits to Semiclassical Concentration: Global Convergence of the Canonical Evolutionary Strategy

arXiv:2605.30371v1 Announce Type: cross Abstract: We address the issue of global convergence in stochastic continuous optimization. For that purpose, we formulate the Canonical Evolutionary Strategy (

Full-field prediction for engineering-scale three-dimensional aircraft with multigrid-hierarchical learning

arXiv:2605.30375v1 Announce Type: cross Abstract: High-fidelity computational fluid dynamics is essential for aerospace design, but engineering-scale simulations of practical three-dimensional aircraf

Functional Attention: From Pairwise Affinities to Functional Correspondences

arXiv:2605.31559v1 Announce Type: new Abstract: Learning mappings between infinite-dimensional function spaces, or operator learning, is essential for many machine learning applications. Although tran

GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement

arXiv:2605.30818v1 Announce Type: cross Abstract: Non-contact material identification enables adaptive interaction for embodied intelligence yet faces challenges from geometry-induced variations (e.g.

Generalizing Multi-Scale Time-Series Modeling with a Single Operator

arXiv:2605.31129v1 Announce Type: new Abstract: Multi-scale modeling has emerged as an effective design principle for time-series forecasting by capturing temporal dynamics at multiple resolutions. As

Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge

arXiv:2605.30568v1 Announce Type: new Abstract: LLM-as-a-Judge is a scalable alternative to human evaluation, yet existing rubric-based methods rely on human-annotated data such as reference answers o

Generative Models and Statistical Validation

arXiv:2605.30453v1 Announce Type: cross Abstract: Generative machine learning has become an essential tool in theoretical and experimental physics, especially in the context of fast surrogates and den

GETA: Generalized Encrypted Traffic Analysis

arXiv:2605.31277v1 Announce Type: cross Abstract: Traditional traffic analysis is being fundamentally challenged by the rapid adoption of encryption, tunnelling, and privacy-preserving protocols, whic

Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings

arXiv:2605.31580v1 Announce Type: new Abstract: Transformer-based architectures have advanced sequence modeling in language and vision, yet general-purpose representation learning for heterogeneous mu

Gradient-Free Training of Spiking Neural Networks via Low-Rank Evolution Strategies

arXiv:2605.30361v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) offer compelling energy efficiency on neuromorphic hardware, yet their training remains challenging because the discret

GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent

arXiv:2603.13875v2 Announce Type: replace Abstract: Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-ca

Graph Neural Networks Are Not Continuous Across Graph Resolutions

arXiv:2605.31315v1 Announce Type: new Abstract: We show that contrary to conventional wisdom in the community, graph neural networks (GNNs) are not continuous with respect to all natural modes of grap

Graphical einops: bridging tensor networks and computation graphs

arXiv:2605.31485v1 Announce Type: new Abstract: Architecture diagrams are ubiquitous in deep learning, but they are usually only representational: the tensor-program identities they suggest are still

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

arXiv:2605.31105v1 Announce Type: new Abstract: Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining

Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine Learning

arXiv:2603.08651v2 Announce Type: replace Abstract: We introduce a comprehensive theoretical and algorithmic framework that bridges formal group theory and group entropies with modern machine learning

HetCCL: Enabling Collective Communication For Mixed-Vendor Heterogeneous Clusters

arXiv:2605.31000v1 Announce Type: cross Abstract: Training Large Language Models (LLMs) on heterogeneous clusters presents significant challenges for collective communication, as hardware from multipl

HiERO-StepG @ Ego4D Step Grounding Challenge: hierarchical activity understanding enables zero-shot step grounding

arXiv:2605.31227v1 Announce Type: new Abstract: Procedural activities follow well-defined structures: whether we consider a cooking recipe or a mechanic repairing a car, these activities naturally dec

High-Load-Density Electro-Permanent Magnetic Foot with Controllable Adhesion for Quadruped Wall-Climbing Robots

arXiv:2605.30849v1 Announce Type: new Abstract: To enable reliable climbing locomotion of quadruped robots on ferromagnetic surfaces, this paper presents a high-load-density electro-permanent magnetic

researcharxiv-cs-ro

HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models

arXiv:2602.21340v2 Announce Type: replace Abstract: Representing the past in a compressed, efficient, and informative manner is a central problem for systems trained on sequential data. The HiPPO fram

How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language

arXiv:2605.30685v1 Announce Type: cross Abstract: AI is being used by people globally, but not everyone is using it in the same ways. Using a large-scale dataset of anonymized, de-identified, and priv

How Much Do LLMs Know About Chinese Zero Pronouns?

arXiv:2605.31056v1 Announce Type: new Abstract: Zero Pronouns (ZPs) are a pervasive linguistic phenomenon in pro-drop languages such as Chinese and have long posed a challenge for natural language pro

HUNT: High-Speed UAV Navigation and Tracking in Unstructured Environments via Instantaneous Relative Frames

arXiv:2509.19452v4 Announce Type: replace-cross Abstract: Search and rescue operations require unmanned aerial vehicles to both traverse unknown unstructured environments at high speed and track targe

Identifying Connectivity Distributions from Neural Dynamics Using Flows

arXiv:2603.26506v2 Announce Type: replace-cross Abstract: Connectivity structure shapes neural computation, but inferring this structure from population recordings is degenerate: multiple connectivity

idSCD: Identifying Training Datasets through Semantic Correlation Descriptors

arXiv:2605.30462v1 Announce Type: cross Abstract: Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave dataset-specific traces in a model

Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness

arXiv:2605.30745v1 Announce Type: new Abstract: Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. Howe

Improved Distribution Estimation in ell_infty

arXiv:2605.30509v1 Announce Type: cross Abstract: We present improved bounds for estimating discrete probability distributions under the ell_infty norm. These include minimax bounds in expectation and

Improved Guarantees for Langevin Monte Carlo with Average Smoothness

arXiv:2605.31413v1 Announce Type: cross Abstract: We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein

Improving Selective Classification with Pairwise Queries for Binary Classification

arXiv:2605.30615v1 Announce Type: new Abstract: In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which

Incremental BPE Tokenization

arXiv:2605.30813v1 Announce Type: new Abstract: We propose a novel algorithm for incremental Byte Pair Encoding (BPE) tokenization. The algorithm processes each input byte in worst-case O(log^2 t) tim

Inferring Events from Time Series using Language Models

arXiv:2503.14190v3 Announce Type: replace Abstract: A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can

IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference

arXiv:2511.21513v2 Announce Type: replace Abstract: Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary m

'Intelegi Romaneste?'' A Recipe for Romanian Vision-Language Models

arXiv:2605.31401v1 Announce Type: new Abstract: Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchmarks but sharply degrading on low-resource languag

Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach

arXiv:2605.30903v1 Announce Type: cross Abstract: Inverse reinforcement learning (IRL) typically assumes demonstrations from a single optimal demonstrator, but in many applications data come from mult

Inverting Data Transformations via Diffusion Sampling

arXiv:2602.08267v2 Announce Type: replace-cross Abstract: We study the problem of transformation inversion on general Lie groups: a datum is transformed by an unknown group element, and the goal is to

IRIS: time-structured manifold projections

arXiv:2605.30810v1 Announce Type: new Abstract: High-dimensional biomedical data, such as cell-by-gene matrices, are increasingly generated temporally. However, Manifold Learning algorithms, like t-SN

Is Memorization Helpful or Harmful? Prior Information Sets the Threshold

arXiv:2602.09405v2 Announce Type: replace-cross Abstract: We examine the connection between training error and generalization error for arbitrary estimating procedures, working in an overparameterized