Search: “research”

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS

arXiv:2605.30748v1 Announce Type: cross Abstract: We present Chatterbox-Flash, a zero-shot text-to-speech model obtained by fine-tuning a pretrained autoregressive TTS decoder into a block-diffusion d

Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects

DGX agent

arXiv:2605.31522v1 Announce Type: new Abstract: Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecul

researcharxiv-cs-lg

1 Jun 2026

China has approved the world’s first invasive brain-computer chip—here’s what’s next

One day last October, sitting in the courtyard of his house in China’s Henan province, Dong Hui decided to see if he could hold a pen to write. Dong, 39, had sustained spinal cord injuries in a car ac

researchmit-tech-review

Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE Solving and Visual Perception

arXiv:2603.23977v2 Announce Type: replace-cross Abstract: Deep networks often rely on architectural heuristics to shape representation evolution, limiting their ability to model data governed by intri

Clustering Guided Domain-Specific Pretrained Foundation Model Very High-Resolution Arctic Remote Sensing

arXiv:2605.30467v1 Announce Type: new Abstract: This study introduces a novel Arctic-focused remote sensing foundation model (RSFM) by combining diversity-aware regional-scale image curation with mask

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

arXiv:2605.31058v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Langu

Conformal C2ST: Turning weak classifiers into strong two-sample tests

arXiv:2507.17026v2 Announce Type: replace-cross Abstract: The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn f

Conformal Reliability: A New Evaluation Metric for Conditional Generation

arXiv:2605.30807v1 Announce Type: new Abstract: Conditional generative models have recently achieved remarkable success in various applications. However, a suitable metric for evaluating the reliabili

Consolidating Rewarded Perturbations for LLM Post-Training

arXiv:2605.31494v1 Announce Type: new Abstract: Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by

Context-Free Recognition with Transformers

arXiv:2601.01754v3 Announce Type: replace-cross Abstract: Transformers excel empirically on tasks that process well-formed inputs according to some grammar, such as natural language and code. However,

Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion Models

arXiv:2605.30631v1 Announce Type: cross Abstract: While automated diagnosis systems have achieved remarkable success in computed tomography (CT)-based lung cancer screening, their development remains

Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference

arXiv:2605.31239v1 Announce Type: cross Abstract: Bagging-based ensembles, most notably Adaptive Random Forests, are among the strongest performers for learning from data streams. A common denominator

Model Releases

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

model-releasesarxiv-cs-ai

arXiv:2605.30611v1 Announce Type: cross Abstract: Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains

Cross-Layer Subspace Coupling for LLM Compression: A Unifying Framework and Its Empirical Limits

arXiv:2605.30836v1 Announce Type: new Abstract: Recent SVD based compression methods for large language models like SVD LLM and Basis Sharing can be unified under one optimization problem. While mathe

Cross-Lingual Steering for Figurative Language Generation

arXiv:2605.30443v1 Announce Type: new Abstract: Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reu

D-SECURE: Dual-Source Evidence Combination for Unified Reasoning in Misinformation Detection

arXiv:2602.14441v2 Announce Type: replace Abstract: Multimodal misinformation increasingly mixes realistic im-age edits with fluent but misleading text, producing persuasive posts that are difficult t

Applications

D^3: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training

arXiv:2605.31164v1 Announce Type: cross Abstract: Training data plays a central role in large language models (LLMs) optimization, motivating extensive research on data scheduling strategies. Most exi

applicationsarxiv-cs-ai

DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

arXiv:2605.30859v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail r

Data-driven Progressive Discovery of Physical Laws

arXiv:2603.13727v2 Announce Type: replace Abstract: Symbolic regression is a powerful tool for knowledge discovery, enabling the extraction of interpretable mathematical expressions directly from data

De-attribute to Forget for LLM Unlearning

arXiv:2605.30919v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns on the use of inappropriate data for training, which has led to a growing in

DeblurSplat: SfM-free 3D Gaussian Splatting with Event Camera for Robust Deblurring

arXiv:2509.18898v2 Announce Type: replace Abstract: In this paper, we propose the first Structure-from-Motion (SfM)-free deblurring 3D Gaussian Splatting method via event camera, dubbed DeblurSplat. W

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

arXiv:2605.31336v1 Announce Type: new Abstract: Recent advances in video generative models have promoted rapid progress in controllable world models. However, maintaining fine-grained spatio-temporal

Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation

arXiv:2509.02970v3 Announce Type: replace Abstract: Partial participation is essential for communication-efficient federated learning at scale, yet existing Byzantine-robust methods typically assume f

DEM: A Distilled Explanation Model for Interpretable Anomaly Detection in Physiological Sensor Networks

arXiv:2605.31007v1 Announce Type: cross Abstract: Anomaly detection in physiological sensor data from Wireless Body Area Networks (WBANs) can be caused by sensor faults, network disruptions, or missin

DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphs

arXiv:2605.31427v1 Announce Type: new Abstract: Dynamic graph learning (DGL) is essential for modelling evolving graph data, but existing methods suffer from significant computational overhead due to

dgMARK: Decoding-Guided Watermarking for Diffusion Language Models

arXiv:2601.22985v2 Announce Type: replace Abstract: We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can gen

DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analytics

arXiv:2605.30538v1 Announce Type: new Abstract: Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records

Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic Interpretability

arXiv:2605.30482v1 Announce Type: new Abstract: Machine learning is increasingly used in mathematical discovery, but in mathematics the desired output is often not a prediction itself, but an explicit

Discovering Differences in Strategic Behavior Between Humans and LLMs

arXiv:2602.10324v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly deployed in social and strategic scenarios, it becomes critical to understand where and why their b

Discovering Thermodynamically Admissible Dissipation Potentials via Grammar-Based Symbolic Regression

arXiv:2605.31532v1 Announce Type: cross Abstract: Constitutive laws for inelastic materials must satisfy strict thermodynamic admissibility requirements, yet current data-driven approaches sacrifice i

DisPlace: Discriminative Place Projections for Multi-Reference Visual Place Recognition

arXiv:2605.30769v1 Announce Type: new Abstract: A key challenge in Visual Place Recognition (VPR) is matching query images against reference maps captured under diverse environmental conditions and vi

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models

arXiv:2605.31293v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently memorize sensitive training data thereby creating significant privacy and copyright risks. Addressing these risk

Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models

arXiv:2605.30713v1 Announce Type: cross Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their applicati

Domain Adaptation and Reasoning Frameworks in Language Models: A Controlled Experiment with Historical Cosmology

arXiv:2605.30415v1 Announce Type: cross Abstract: We investigate how domain adaptation reshapes explanatory behavior in language models using historical cosmology as a controlled setting. In Phase 1,

Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold

arXiv:2601.21686v2 Announce Type: replace Abstract: Key-value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capaci

DRIFT: Joint Channel Estimation and Prediction Towards Pilotless 6G Non-Terrestrial Networks

arXiv:2605.31065v1 Announce Type: cross Abstract: Non-terrestrial networks (NTNs) are expected to play a pivotal role in sixth-generation (6G) systems by enabling ubiquitous connectivity and massive c

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training

arXiv:2512.13996v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-k routing imposes a rigid sparsit

Dynamical local Frechet curve regression in manifolds

arXiv:2505.05168v3 Announce Type: replace-cross Abstract: Under mild conditions, this paper derives a least-squares local linear Frechet curve predictor for response and regressor evaluated in a separ

Early Prediction of Future Behavioral Strategy from Process Traces

arXiv:2605.30550v1 Announce Type: new Abstract: Adaptive systems often need to make task-specific decisions about people from limited evidence: a tutor may need to anticipate how a learner will approa

EBuddy: a workflow orchestrator for industrial human-machine collaboration

arXiv:2603.28579v2 Announce Type: replace Abstract: This paper presents EBuddy, a voice-guided workflow orchestrator for natural human-machine collaboration in industrial environments. EBuddy targets

researcharxiv-cs-ro

EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment

arXiv:2602.01173v3 Announce Type: replace Abstract: Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowerin

Effective Biological Representation Learning by Masking Gene Expression

arXiv:2605.31562v1 Announce Type: new Abstract: RNA sequencing produces rich and diverse datasets of gene expression, offering compelling insights into cellular state and function that have many appli

Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation

arXiv:2605.30753v1 Announce Type: new Abstract: Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many

EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context

arXiv:2503.05846v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved impressive progress across a wide range of tasks, yet their heavy reliance on English-centric train

Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models

arXiv:2603.19262v2 Announce Type: replace-cross Abstract: Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentati

Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization

arXiv:2605.30928v1 Announce Type: new Abstract: Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward

researcharxiv-cs-ro

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

arXiv:2605.30521v1 Announce Type: new Abstract: Large language models must frequently process untrusted inputs, such as judging an answer from another model or running tasks like spam and harm classif

Evidence for systematic semantic structure in individual phonemes

arXiv:2603.17306v3 Announce Type: replace Abstract: A foundational assumption in linguistics holds that sound-meaning relations are largely arbitrary. Here we show that this assumption fails at the le