model releases

CADET: A Modular Platform for Evaluating Distributed Cooperative Autonomy in Connected Autonomous Vehicles

model-releasesarxiv-cs-lg

arXiv:2606.04072v1 Announce Type: cross Abstract: Deep learning models are increasingly central to autonomous vehicle (AV) pipelines, yet their integration has traditionally followed a monolithic desi

Model Releases

Caliper: Probing Lexical Anchors versus Causal Structure in LLMs

DGX agent

arXiv:2606.04915v1 Announce Type: new Abstract: Large language models reach 50 to 70% accuracy on causal reasoning benchmarks such as CLadder, but it is unclear whether this reflects structural reason

model-releasesarxiv-cs-cl

4 Jun 2026

Can Generalist Agents Automate Data Curation?

arXiv:2606.04261v1 Announce Type: new Abstract: Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement,

Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA

arXiv:2606.04262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the

Can Large Language Models Generalize Procedures Across Representations?

arXiv:2602.03542v2 Announce Type: replace Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are o

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

arXiv:2606.04141v1 Announce Type: cross Abstract: LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt inj

CDPM-Align: Multi-Scale Guidance-Aligned Diffusion Pretraining for Robust Few-Shot Anatomical Landmark Detection

arXiv:2606.04898v1 Announce Type: new Abstract: Anatomical landmark detection is a fundamental task in medical image analysis supporting a wide range of diagnostic and interventional workflows. Althou

ChannelTok: Efficient Flexible-Length Vision Tokenization

arXiv:2606.04461v1 Announce Type: new Abstract: Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoder

ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess

arXiv:2606.04473v1 Announce Type: cross Abstract: We present ChessMimic, a system of three small encoder-only transformers - for move, thinking-time, and outcome prediction - conditioned on the positi

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

arXiv:2606.04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated enviro

COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations

arXiv:2606.04604v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent p

Constraint-Enhanced Physical Search through Correlation Matching

arXiv:2606.03554v1 Announce Type: cross Abstract: Physical systems do not merely add noise to search processes; they impose constraints that generate structured correlations. We propose a principle of

Continual Visual and Verbal Learning Through a Child's Egocentric Input

arXiv:2606.05115v1 Announce Type: cross Abstract: Children learn the meanings of words from a continuous, temporally structured stream of egocentric experience. Recent work shows that neural networks

CoPark: Learning Reactive Parking via Self-Play

model-releasesarxiv-cs-ro

arXiv:2606.04149v1 Announce Type: new Abstract: Learning a single policy that reaches a goal with high geometric precision while interacting safely with nearby agents poses conflicting objectives. Pre

Curvature-aware dynamic precision approach for physics-informed neural networks

arXiv:2606.04736v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have become a promising framework for simulating partial differential equations (PDEs) by embedding physical

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities

arXiv:2606.04460v1 Announce Type: cross Abstract: AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. How

D^3-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous Driving

model-releasesarxiv-cs-ro

arXiv:2606.04884v1 Announce Type: new Abstract: Traditional end-to-end autonomous driving frameworks frequently suffer from the 'style-averaging' dilemma when trained on high-variance human demonstrat

DeepSeek is becoming more popular among US enterprises as companies look for cheaper alternatives to Anthropic and OpenAI “DeepSeek takes to…

model-releasesclem-delangue--x

DeepSeek is becoming more popular among US enterprises as companies look for cheaper alternatives to Anthropic and OpenAI “DeepSeek takes top spot on 'trending' list as companies look for alternatives

DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities

arXiv:2606.04205v1 Announce Type: cross Abstract: The growing popularity and capacity of generative models have eroded the distinction between human and machine-generated content, motivating a growing

Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

arXiv:2606.04109v1 Announce Type: new Abstract: Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but th

Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation

arXiv:2606.04046v1 Announce Type: cross Abstract: In embodied vision-language decision making tasks such as robotic manipulation and navigation, Vision-Language and Vision-Language-Action Models (VLMs

DLLG: Dynamic Logit-Level Gating of LLM Experts

arXiv:2606.04378v1 Announce Type: new Abstract: Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prem

DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics

model-releasesarxiv-cs-ro

arXiv:2606.04206v1 Announce Type: new Abstract: We address the challenge of enabling robots to manipulate deformable linear objects (DLOs), such as ropes, cables, and rubber bands. Prior work has prim

DMAConv: Dual Mask-Adaptive Convolution for Remote Sensing Pansharpening

arXiv:2512.08331v2 Announce Type: replace Abstract: Pansharpening aims to fuse a high-resolution panchromatic image with a low-resolution multispectral image. Existing deep learning methods, including

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

arXiv:2606.04115v1 Announce Type: cross Abstract: Quantizing large language models (LLMs) to low-precision floating-point representations is central to efficient deployment, yet applying a single bit-

Do Transformers Need Three Projections? Systematic Study of QKV Variants

arXiv:2606.04032v1 Announce Type: cross Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role

Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?

arXiv:2606.04811v1 Announce Type: new Abstract: Video generation models have made impressive strides in synthesizing visually compelling content, yet their outputs remain confined to the virtual domai

Dreaming: Better memory for a more helpful ChatGPT

OpenAI's 'Dreaming' feature enhances ChatGPT's memory capabilities by allowing the model to retain and leverage information from previous conversations to provide more personalized and contextually aw

model-releasesopenai

Ekka: Automated Diagnosis of Silent Errors in LLM Inference

arXiv:2606.04594v1 Announce Type: cross Abstract: LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introd

Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding

arXiv:2604.00819v2 Announce Type: replace-cross Abstract: Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact thro

Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases

arXiv:2606.05112v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed as clinical agents, yet static, single-turn benchmarks cannot capture how a model dynamically del

Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction

arXiv:2602.23312v3 Announce Type: replace-cross Abstract: Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging f

EvoPrompt: Guided Prompt Evolution for Vision-Language Models Adaptation

arXiv:2603.09493v2 Announce Type: replace-cross Abstract: The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. Whi

Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions

arXiv:2606.04197v1 Announce Type: cross Abstract: How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choice

Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models

arXiv:2510.20042v3 Announce Type: replace Abstract: Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I)

Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up…

Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up to 100hrs, and is confident enough to put a financial guarant

model-releasesswyx--x

FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs

arXiv:2606.04282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, a

FinTradeBench: A Financial Reasoning Benchmark for LLMs

arXiv:2603.19225v3 Announce Type: replace-cross Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamenta

Flow Matching Calibration for Simulation-Based Inference under Model Misspecification

model-releasesarxiv-cs-lg

arXiv:2509.23385v5 Announce Type: replace-cross Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simu

Food-R1: A Unified Multi-Task Food Vision-Language Model with Reinforcement Learning

arXiv:2606.04986v1 Announce Type: new Abstract: Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (S

foom!

model-releasesemad-mostaque--x

foom! Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we t

Founders Fund launches a TV-style game show featuring A-list founders and investors, including Sam Altman and Palmer Luckey, playing a game of Mafia (Tom Dotan/Newcomer)

Tom Dotan / Newcomer: Founders Fund launches a TV-style game show featuring A-list founders and investors, including Sam Altman and Palmer Luckey, playing a game of Mafia — Do people want to watch the

model-releasestechmeme

From Symbolic to Geometric: Enabling Spatial Reasoning in Large Language Models

arXiv:2606.04381v1 Announce Type: cross Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely symbolic, arising from patt

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

arXiv:2606.04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory

GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes

arXiv:2606.05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customiz

GENEB: Why Genomic Models Are Hard to Compare

arXiv:2606.04525v1 Announce Type: new Abstract: Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reportin

Geometry-Aware Hallucination Detection in Large Language Models

arXiv:2601.06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior wor

Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting

arXiv:2606.05124v1 Announce Type: cross Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface represen