model releases

Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction

arXiv:2305.12678v3 Announce Type: replace Abstract: Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-

Model Releases

GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms

DGX agent

arXiv:2605.11117v1 Announce Type: new Abstract: Scientific discovery can be modeled as a sequence of probabilistic decisions that map physical problems to numerical solutions. Recent agentic AI system

model-releasesarxiv-cs-lg

13 May 2026

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models

arXiv:2605.12327v1 Announce Type: new Abstract: A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scal

Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes

arXiv:2605.06152v2 Announce Type: replace-cross Abstract: Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the 'Slingshot Mechanism.' Ex

GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs

arXiv:2503.06139v2 Announce Type: replace Abstract: Pairwise LLM-as-a-judge evaluation asks the judge to identify the better of two candidate answers. We study a one-line modification that asks for th

gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods

arXiv:2605.11355v1 Announce Type: new Abstract: Inventory-policy comparisons are often difficult to interpret because performance depends on the evaluation contract as much as on the policy itself. Di

HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench

arXiv:2601.20255v2 Announce Type: replace-cross Abstract: SWE-bench has emerged as the premier benchmark for evaluating Large Language Models on complex software engineering tasks. While these capabil

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model

arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini

hey surprise - you can just launch interactive in tmux and then tail the jsonl - shipped a small wrapper...ralph loop iterating to full pari…

model-releasesjeremy-howard--x

hey surprise - you can just launch interactive in tmux and then tail the jsonl - shipped a small wrapper...ralph loop iterating to full parity rn https://github.com/dexhorthy/shannon Starting June 15,

Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation

arXiv:2605.11208v1 Announce Type: new Abstract: Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain chall

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer

arXiv:2605.11061v1 Announce Type: new Abstract: The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In

Holder Policy Optimisation

arXiv:2605.12058v1 Announce Type: new Abstract: Group Relative Policy Optimisation (GRPO) enhances large language models by estimating advantages across a group of sampled trajectories. However, mappi

How do you keep Claude working until the job is done? Claude Code helps with this in a few ways, including one we shipped recently: /goal.

model-releasesboris-cherny--x

Claude Code includes a `/goal` feature that helps maintain task continuity and ensure Claude continues working until a job is completed. This feature, recently shipped, is one of several ways Claude C

How Glance turns hours of video into mobile-ready clips with AI

model-releasesgoogle-cloud-ai

Every day, thousands of hours of new video content sits waiting to be discovered. Most of it lives in long-form, horizontal formats, while audiences are scrolling through vertical feeds on their phone

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they c…

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kin

model-releasesdair-ai--x

Human-Grounded Multimodal Benchmark with 900K-Scale Aggregated Student Response Distributions from Japan's National Assessment of Academic Ability

arXiv:2605.11663v1 Announce Type: new Abstract: Authentic school examinations provide a high-validity test bed for evaluating multimodal large language models (MLLMs), yet benchmarks grounded in Japan

Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference

arXiv:2505.13770v3 Announce Type: replace-cross Abstract: Reliable causal inference is essential for making decisions in high-stakes areas like medicine, economics, and public policy. However, it rema

If you use any of the following with your Claude sub, your usage must got cut by 25x: - T3 Code - Conductor - zed - jean - “Claude -p” in yo…

model-releasesjeremy-howard--x

If you use any of the following with your Claude sub, your usage must got cut by 25x: - T3 Code - Conductor - zed - jean - “Claude -p” in your ci - scripts to call Claude code from other tools They’re

Improving the Accuracy of Amortized Model Comparison with Self-Consistency

arXiv:2508.20614v3 Announce Type: replace-cross Abstract: Amortized Bayesian model comparison (BMC) enables fast probabilistic ranking of models via simulation-based training of neural surrogates. How

Instagram rolls out Instants, which lets users share ephemeral photos, as an in-app feature in Instagram and as a standalone app in select countries (Zac Hall/9to5Mac)

Zac Hall / 9to5Mac: Instagram rolls out Instants, which lets users share ephemeral photos, as an in-app feature in Instagram and as a standalone app in select countries — Meta just launched a brand ne

model-releasestechmeme

Intention-Conditioned Flow Occupancy Models

arXiv:2506.08902v4 Announce Type: replace Abstract: Large-scale pre-training has fundamentally changed how machine learning research is done today: large foundation models are trained once, and then c

Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS

arXiv:2605.12200v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings.

KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks

arXiv:2605.12306v1 Announce Type: cross Abstract: Catastrophic forgetting remains the central obstacle in continual learning (CL): parameters shared across tasks interfere with one another, and existi

Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions

arXiv:2605.12118v1 Announce Type: cross Abstract: For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference

arXiv:2605.12471v1 Announce Type: cross Abstract: We introduce KV-Fold, a simple, training-free long-context inference protocol that treats the key-value (KV) cache as the accumulator in a left fold o

Large-Small Model Collaboration for Farmland Semantic Change Detection

arXiv:2605.12282v1 Announce Type: new Abstract: Farmland Semantic Change Detection (SCD) is essential for cultivated land protection, yet existing benchmarks and models remain insufficient for fine-gr

Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection

arXiv:2605.12156v1 Announce Type: new Abstract: Automatic misinformation detection performs well when deception is visible in what an article explicitly states. However, some misinformation articles r

LatentHDR: Decoupling Exposure from Diffusion via Conditional Latent-to-Latent Mapping for Text/Image-to-Panoramic HDR

arXiv:2605.11115v1 Announce Type: new Abstract: High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionb

Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation

arXiv:2602.14199v2 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis. However, the number of Gaussian primitives often gro

Learning Compact Boolean Networks

arXiv:2602.05830v2 Announce Type: replace-cross Abstract: Floating-point neural networks dominate modern machine learning but incur substantial inference costs, motivating emerging interest in Boolean

Learning, Fast and Slow: Towards LLMs That Adapt Continually

arXiv:2605.12484v1 Announce Type: new Abstract: Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to a

Learning Subspace-Preserving Sparse Attention Graphs from Heterogeneous Multiview Data

arXiv:2605.11881v1 Announce Type: new Abstract: The high-dimensional features extracted from large-scale unlabeled data via various pretrained models with diverse architectures are referred to as hete

Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

arXiv:2605.11739v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute t

Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration

arXiv:2605.12084v1 Announce Type: cross Abstract: Designing learnable information-theoretic objectives for robot exploration remains challenging. Such objectives aim to guide exploration toward data t

Less than one hour until Falcon 9’s launch of Dragon’s 34th Commercial Resupply Services mission to the @Space_Station. Teams continue to mo…

model-releaseselon-musk--x

Less than one hour until Falcon 9’s launch of Dragon’s 34th Commercial Resupply Services mission to the @Space_Station. Teams continue to monitor weather, which is currently 10% favorable for liftoff

LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing

arXiv:2605.11508v1 Announce Type: new Abstract: Currently, there is a gap in the field of ultra-high-definition (UHD) video dehazing due to the lack of a benchmark for evaluation. Furthermore, existin

Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction

arXiv:2605.11354v1 Announce Type: new Abstract: Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering str

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

arXiv:2605.11872v1 Announce Type: new Abstract: Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing me

Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs

arXiv:2509.19207v2 Announce Type: replace Abstract: Contrastive vision-language models (VLMs) have made significant progress in binding visual and textual information, yet understanding long, composit

LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues

arXiv:2605.12493v1 Announce Type: new Abstract: Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workfl

Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks

arXiv:2605.11209v1 Announce Type: new Abstract: While existing benchmarks demonstrate the near-perfect performance of large language models (LLMs) on various tasks, this apparent saturation often obsc

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering

arXiv:2605.12361v1 Announce Type: new Abstract: Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain dis

MEME: Multi-entity & Evolving Memory Evaluation

arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding

arXiv:2605.12185v1 Announce Type: new Abstract: Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect para

Modality-Inconsistent Continual Learning of Multimodal Large Language Models

arXiv:2412.13050v2 Announce Type: replace-cross Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language M

More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing

arXiv:2605.11836v1 Announce Type: cross Abstract: Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabiliti

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models

arXiv:2501.02955v2 Announce Type: replace Abstract: In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grain

MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation

arXiv:2605.12134v1 Announce Type: new Abstract: Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There