model releases

SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models

arXiv:2605.10576v1 Announce Type: cross Abstract: Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpr

Model Releases

Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought

DGX agent

arXiv:2605.09906v1 Announce Type: new Abstract: Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cros

model-releasesarxiv-cs-ai

12 May 2026

Sequential Causal Discovery with Noisy Language Model Priors

arXiv:2506.16234v2 Announce Type: replace Abstract: Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data oft

Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data

arXiv:2605.09746v1 Announce Type: cross Abstract: Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic i

Set Prediction for Next-Day Active Fire Forecasting

arXiv:2605.10298v1 Announce Type: new Abstract: Accurate next-day active fire forecasts can support early warning, disaster response, forest risk assessment, and downstream estimation of fire-related

simpleposter: a simple baseline for product poster generation

arXiv:2605.08784v1 Announce Type: new Abstract: Product poster generation poses distinct challenges beyond general poster design, requiring both faithful preservation of product appearance and precise

Simultaneous Long-tailed Recognition and Multi-modal Fusion for Highly Imbalanced Multi-modal Data

arXiv:2605.10498v1 Announce Type: cross Abstract: Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority c

Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success

arXiv:2605.09070v1 Announce Type: cross Abstract: Many jailbreak attack research papers report attack success rates for a limited number of parameter settings, even though there are many combinations

Single-Thread JPEG Decoder Benchmarks Mis-Evaluate ML Data Loaders

arXiv:2605.08731v1 Announce Type: cross Abstract: JPEG decode is routine ML infrastructure, but Python decoder choices are often justified by single-process, single-thread microbenchmarks. We audit th

Sinkhorn Treatment Effects: A Causal Optimal Transport Measure

arXiv:2605.08485v1 Announce Type: cross Abstract: We introduce the Sinkhorn treatment effect, an entropic optimal transport measure of divergence between counterfactual distributions. Unlike classical

Sketch-and-Verify: Structured Inference-Time Scaling via Program Sketching

arXiv:2605.08658v1 Announce Type: cross Abstract: SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a sma

SLAM: Structural Linguistic Activation Marking for Language Models

arXiv:2605.05443v2 Announce Type: replace-cross Abstract: LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for de

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation

arXiv:2605.10376v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliabl

SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing

arXiv:2605.10831v1 Announce Type: cross Abstract: Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information

SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications

arXiv:2605.09610v1 Announce Type: cross Abstract: We introduce SmartEval, a benchmark for systematically evaluating the quality of Solidity smart contracts generated by large language models (LLMs) fr

SMIXAE: Towards Unsupervised Manifold Discovery in Language Models

arXiv:2605.09224v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models.

SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy

arXiv:2605.09598v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos du

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

arXiv:2605.09063v1 Announce Type: new Abstract: Following the recent achievement of gold-medal performance on the IMO by frontier LLMs, the community is searching for the next meaningful and challengi

Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection

arXiv:2605.08583v1 Announce Type: new Abstract: Large language models are increasingly used in scientific writing, yet they can fabricate citation-shaped references that appear plausible but fail bibl

Sources: Anthropic is in talks to raise between 30B and 50B in a funding round that would value it at up to $950B (Mike Isaac/New York Times)

Mike Isaac / New York Times: Sources: Anthropic is in talks to raise between 30B and 50B in a funding round that would value it at up to 950B — The start-up, which recently released a powerful A.I. mo

model-releasestechmeme

SpaceX is officially my fav art account now

model-releaseselon-musk--x

SpaceX's official social media account is being praised for its engaging visual content and aesthetic presentation, earning recognition as a favorite among followers for its artistic approach to shari

Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers

arXiv:2605.09403v1 Announce Type: cross Abstract: Architectural choices inside the Transformer feedforward network (FFN) block do not merely affect the block itself; they reshape the computations lear

SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

arXiv:2602.03916v3 Announce Type: replace-cross Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet it remains a major challenge for contemporary vision-language models (VLMs).

SPDEBench: An Extensive Benchmark for Learning Stochastic PDEs

arXiv:2505.18511v2 Announce Type: replace Abstract: Stochastic Partial Differential Equations (SPDEs) driven by random noise play a central role in modeling physical processes with rough spatio-tempor

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

arXiv:2601.11042v2 Announce Type: replace-cross Abstract: Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for para

SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data

arXiv:2508.08441v3 Announce Type: replace-cross Abstract: Automated molecular structure elucidation remains challenging, as existing approaches often depend on pre-compiled databases or restrict thems

Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models

arXiv:2605.09031v1 Announce Type: new Abstract: Energy-based models (EBMs) are flexible generative architectures inspired by statistical physics, but their learning and generative properties remain po

Statistical Model Checking of the Keynes+Schumpeter Model: A Transient Sensitivity Analysis of a Macroeconomic ABM

arXiv:2605.10447v1 Announce Type: cross Abstract: Agent-based models (ABMs) are increasingly used in macroeconomics, but their analysis still often relies on ad hoc Monte Carlo campaigns with heteroge

Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols

arXiv:2605.09618v1 Announce Type: new Abstract: When should a language model answer directly, sample and vote, or engage in multi-agent debate? Recent work shows voting often explains much of the gain

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

arXiv:2604.02608v2 Announce Type: replace Abstract: Activation steering presupposes that task-relevant behaviors correspond to linear directions in activation space -- directions that should both stee

Step Rejection Fine-Tuning: A Practical Distillation Recipe

arXiv:2605.10674v1 Announce Type: cross Abstract: Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the

Strategic commitments shape collective cybersecurity under AI inequality

arXiv:2605.09415v1 Announce Type: new Abstract: The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence to

Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust

arXiv:2605.10059v1 Announce Type: new Abstract: Agent-based modeling (ABM) has long been used in economics to study human behavior, and large language model (LLM) agents now enable new forms of social

Structure-Preserving Reconstruction of Convex Lipschitz Functionals on Hilbert Spaces from Finite Samples

arXiv:2605.08559v1 Announce Type: cross Abstract: Convex functionals are ubiquitous in applied analysis, appearing as value functions, risk measures, super-hedging prices, and loss functionals in mach

SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution

arXiv:2605.08366v1 Announce Type: new Abstract: We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test W

SYNCR: A Cross-Video Reasoning Benchmark with Synthetic Grounding

arXiv:2605.08412v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent

Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data

arXiv:2605.10129v1 Announce Type: new Abstract: Large language models (LLMs) rely on web-scale corpora for pre-training. The noise inherent in these datasets tends to obscure meaningful patterns and u

TabPFN-3 just released: a pre-trained tabular foundation model for up to 1M rows [R][N]

model-releasesr-machinelearning

TabPFN-3 is a pre-trained tabular foundation model that supports datasets up to 1,000,000 rows × 200 features , representing a significant scaling improvement for the TabPFN family. The model delivers

Tabular Foundation Model for Generative Modelling

arXiv:2605.09424v1 Announce Type: new Abstract: Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modality, r

TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems

arXiv:2605.09539v1 Announce Type: new Abstract: Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically

Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation

arXiv:2505.11604v5 Announce Type: replace Abstract: Editing presentation slides is a frequent yet tedious task, ranging from creative layout design to repetitive text maintenance. While recent GUI-bas

Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning

arXiv:2605.10247v1 Announce Type: new Abstract: Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely o

TeleResilienceBench: Quantifying Resilience for LLM Reasoning in Telecommunications

arXiv:2605.09929v1 Announce Type: new Abstract: Deploying large language models in telecommunications requires more than task accuracy. In realistic workflows, a model may inherit partially completed

'tell me about recent funding and news for openai and anthropic' result with @wokeloai mcp included today's trial, tomoro acquisition, and c…

model-releasesyohei-nakajima--x

Yohei Nakajima shared recent funding and news updates about OpenAI and Anthropic on X, including information about a trial involving the wokeloai MCP, a tomorrow acquisition, and additional details (c

Test-Time Speculation

arXiv:2605.09329v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its perfo

Text-Guided Multi-Scale Frequency Representation Adaptation

arXiv:2605.08181v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning methods introduce a small number of training parameters, enabling pre-trained models to adapt rapidly to new data dist

TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models

arXiv:2605.06047v2 Announce Type: replace-cross Abstract: Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance thr

The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection

arXiv:2605.10334v1 Announce Type: new Abstract: Recent deepfake detection methods demonstrate improved cross-dataset generalization, yet the underlying mechanisms remain underexplored. We introduce th