model releases

Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy

arXiv:2509.17901v4 Announce Type: replace Abstract: Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines, not because they fail,

Model Releases

Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families

DGX agent

arXiv:2606.21249v1 Announce Type: new Abstract: Retrieval heads, attention heads that copy information from earlier context to the current position, have been proposed as the mechanistic substrate for

model-releasesarxiv-cs-lg

23 Jun 2026

Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks

arXiv:2506.23053v3 Announce Type: replace Abstract: Urban sensor networks need forecasts that are accurate, carry useful uncertainty, and refresh fast enough to act on as new readings arrive. These go

DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppression

arXiv:2606.22625v1 Announce Type: new Abstract: Degraded document image binarization is sensitive to domain shifts caused by paper aging, bleed-through, stains, shadows, and uneven illumination, and t

DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction

arXiv:2606.23031v1 Announce Type: new Abstract: Reconstructing dynamic urban scenes remains challenging due to the unbounded nature of driving environments and the presence of multiple dynamic objects

DrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation

arXiv:2606.20663v1 Announce Type: cross Abstract: Large Language Models have the potential to expand and improve the access to clinical information by enabling new ways of interacting with medical kno

Duet: Dual-Robot Understanding via Efficient Teaching

arXiv:2606.20990v1 Announce Type: new Abstract: Dual-robot collaboration enables tasks that exceed the reach and payload of a single robot, such as collaboratively transporting objects across environm

Dynamics, stability, and energy efficiency of an energy-recycling rimless wheel with spring-clutch legs

arXiv:2606.22073v1 Announce Type: new Abstract: This paper proposes an energy-recycling rimless wheel with spring-clutch legs. The proposed mechanism uses a lockable clutch to store part of the impact

Each Judge Its Own Yardstick: Discovering Per-VLM Taxonomies for Physical Video Evaluation

arXiv:2606.22918v1 Announce Type: new Abstract: Maintaining physical consistency in video generators and world models increasingly relies on vision-language models (VLMs) as automated judges that prov

Early-Exit Graph Neural Networks for Link Prediction

arXiv:2606.22167v1 Announce Type: new Abstract: Graph Neural Networks are great for link prediction in various network-like structures; however, the question of their speed/quality tradeoff has been b

EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies

arXiv:2606.18239v2 Announce Type: replace Abstract: We present EBench, a simulation benchmark that diagnoses generalist mobile manipulation policies beyond a single success-rate scalar. EBench compris

EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction

arXiv:2606.22925v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models increasingly rely on multi-dataset training and evaluation, yet public EEG datasets still lack a shared t

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

arXiv:2510.26113v2 Announce Type: replace Abstract: Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introd

ELADO: Elliptic PDE Assessment Datasets for Operator Learning

arXiv:2606.20771v1 Announce Type: new Abstract: We introduce ELADO (Elliptic PDE Assessment Datasets for Operator Learning), a systematic benchmark suite constructed to show and quantify failure modes

ELDiff: When Evidential Learning Meets Text-to-Image Diffusion

arXiv:2606.20924v1 Announce Type: new Abstract: In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image s

Enhancing Protein Representation Learning via Manifold Restore Mixing

arXiv:2606.22307v1 Announce Type: new Abstract: Data augmentation (DA) has been proven to be an effective means for improving protein representation learning (PRL) by generating additional training sa

ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents

arXiv:2606.22948v1 Announce Type: cross Abstract: As multimodal agents move from interface understanding to real software control, successful trajectory discovery in live desktop environments becomes

Essential Subspace Merging for Multi-Task Learning

arXiv:2606.19164v2 Announce Type: replace Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint

Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs

arXiv:2606.20177v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in various Remote Sensing (RS) tasks. However, their ability to compre

Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability

arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct

Evaluation of Medical Vision Language Models HuluMed and MedGemma, and general purpose chatbots Gemma 3, ChatGPT Plus, and Claude Pro on real previously unseen wound images

arXiv:2606.20723v1 Announce Type: new Abstract: Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular c

Evo-RAD: Navigating Rare Retinal Disease Diagnosis via Self-Evolving Agentic Retrieval

arXiv:2606.22955v1 Announce Type: new Abstract: Large-scale pretrained foundation models have revolutionized general medical screening, but often falter on rare diseases because such conditions are un

Evolving Spatial Weights for Cartographic Synthesis

arXiv:2606.22252v1 Announce Type: new Abstract: The integration of multiple thematic data layers into a single composite map, known as the cartographic synthesis problem, is typically addressed throug

Exabeam launches Praxen, an open-source tool to verify AI agent behavior

model-releasessiliconangle

Security intelligence and management solutions company Exabeam Inc. today introduced Agent Behavior Verification, a pre-deployment security discipline for artificial intelligence agents, and released

Explainable Boosting Machine for Predicting Claim Severity and Frequency in Car Insurance

arXiv:2503.21321v2 Announce Type: replace-cross Abstract: With the rapid development of machine learning and deep learning techniques, actuaries and the broader insurance industry face a persistent tr

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm

arXiv:2509.23946v3 Announce Type: replace Abstract: Many LLMs plan before they act, yet planning and execution are often still entangled in one long generation trace, enforced only through prompts, or

Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial Generalization

arXiv:2606.21100v1 Announce Type: new Abstract: The integration of pretrained encoders with diffusion policies has become a dominant paradigm for visual robotic manipulation. However, it still struggl

Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo

arXiv:2606.22768v1 Announce Type: new Abstract: To make large-scale distributed training practical outside high-bandwidth datacenters, we must reduce blocking, high-volume synchronization. While DiLoC

Falcon 9 launches the Starfall Demo mission from Florida

model-releaseselon-musk--x

Falcon 9 successfully launched the Starfall Demo mission from a Florida launch facility, marking another operational flight for SpaceX's reusable rocket. The mission demonstrates continued progress in

Fara-1.5: Scalable Learning Environments for Computer Use Agents

arXiv:2606.20785v1 Announce Type: cross Abstract: Collecting computer use data from human demonstrations is expensive and slow, motivating the need for scalable generation strategies. This requires tw

FiLM-Coordinated Dual-Branch Transformer for Global-Local Dependency Modeling in Language Modeling

arXiv:2606.21075v1 Announce Type: cross Abstract: Standard Transformers use a single self-attention pathway to model both global dependencies and local patterns, creating tension between long-range st

Finally, get creative! I'm setting up a 'scheduling' channel which lets people tag Claude to find time on our calendars.

Thariq is announcing a new 'scheduling' channel feature that allows users to tag Claude to help coordinate and find available time across multiple calendars. This tool appears designed to streamline m

model-releasesthariq--x

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

arXiv:2606.20246v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion pa

Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design

arXiv:2606.21683v1 Announce Type: cross Abstract: We consider the parameter estimation problem in logistic regression with Gaussian design: the estimation of a fixed unknown parameter heta^*in R^d (|h

FirstPass: Grounding AI Scientific Judgment in Multi-Round Editorial Outcomes

arXiv:2606.20769v1 Announce Type: cross Abstract: AI systems for peer review fail on three fronts: they train on Computer Science and Machine Learning venues alone, ignore the iterative dialogue that

FlowCodec: One-Step Flow Prior for Generative Image Compression

arXiv:2606.21030v1 Announce Type: cross Abstract: Diffusion-based image compression methods, leveraging powerful generative priors, have demonstrated remarkable perceptual quality at ultra-low bitrate

Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation

arXiv:2606.23420v1 Announce Type: new Abstract: Flow matching has recently become a new standard for behavior cloning in robotic manipulation. However, state-of-the-art flow matching policies suffer f

Following the Flow: Advection-Consistent Modeling for Event-based Small Object Detection

arXiv:2606.22378v1 Announce Type: new Abstract: Event cameras enable high-frequency visual perception with microsecond latency, offering advantages for dynamic scenes. However, event-based small objec

From Convolution to Transformer: A Comparative Study of U-Net Variants for Brain Tumor and Retinal Vessel Segmentation

arXiv:2606.22168v1 Announce Type: new Abstract: Medical image segmentation plays an important role in computer aided diagnosis, treatment planning, and disease monitoring. U-Net has been widely used f

From Handcrafted Features to Functional Edge Learning: Evolution of EEG Seizure Detection Frameworks

arXiv:2606.22258v1 Announce Type: new Abstract: Electroencephalogram (EEG) analysis remains the clinical gold standard for epilepsy diagnosis and seizure detection. While Deep Learning (DL) has signif

From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents

arXiv:2606.20661v1 Announce Type: cross Abstract: The integration of external tools has transitioned LLM agents from passive responders to autonomous systems. However, current benchmarks prioritize ex

From Point Estimates to Distributions: GMM Pooling for MIL in Preterm Birth Prediction

arXiv:2606.23005v1 Announce Type: new Abstract: Preterm birth (PTB) prediction can enable targeted surveillance and timely intervention, yet most ultrasound-based models use a single selected transvag

From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa

arXiv:2606.22274v1 Announce Type: cross Abstract: Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources fo

Fursee: Hybrid YOLO-DINOv3 Framework for Fursuit Identity Retrieval and Clustering

arXiv:2606.22872v1 Announce Type: new Abstract: Global furry conventions produce massive fursuit photographs, while manual sorting brings heavy labor costs and calls for automatic identity retrieval a

Generalized nonparametric regression in reproducing kernel Hilbert spaces: Consistency and rates of convergence

arXiv:2606.22993v1 Announce Type: cross Abstract: We develop a comprehensive theory for regularized M-estimation in reproducing kernel Hilbert spaces. Under mild conditions on the loss we establish ex

Generating Fearful Images: Investigating Potential Emotional Biases in Image-Generation Models

arXiv:2411.05985v3 Announce Type: replace-cross Abstract: This paper examines potential biases and inconsistencies in the emotions evoked by images produced by generative artificial intelligence (AI)

GeoFidelity-Bench: Evaluating Segment-Level Geographic Fidelity in Text-to-Image Street-View Generation

arXiv:2606.23669v1 Announce Type: new Abstract: Text-to-image models can generate visually plausible city streets, but whether their outputs correspond to a requested road segment rather than a generi

GEOPHYS: The Geometry of Physical Plausibility

arXiv:2606.20707v1 Announce Type: new Abstract: While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow