Knowledge catalogue
arXiv:2606.00467v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-intern
arXiv:2409.01062v4 Announce Type: replace-cross Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models. While exi
arXiv:2606.01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory,
arXiv:2606.01456v1 Announce Type: cross Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sale
arXiv:2601.22787v2 Announce Type: replace Abstract: Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4
arXiv:2605.30589v1 Announce Type: cross Abstract: U.S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high s
arXiv:2510.05115v3 Announce Type: replace Abstract: Large language models (LLMs) have opened new paradigms in optimization modeling by enabling the generation of executable solver code from natural la
arXiv:2603.00377v2 Announce Type: replace Abstract: Full Waveform Inversion (FWI) is a highly nonlinear and ill-posed problem that aims to recover subsurface velocity maps from surface-recorded seismi
arXiv:2605.30323v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. Howe
arXiv:2605.29280v1 Announce Type: cross Abstract: Knowledge distillation (KD) transfers a single scalar prediction from a large foundation model (FM) to compact vertical models (VMs), suffering from d
arXiv:2605.29101v1 Announce Type: new Abstract: Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups
arXiv:2605.30280v1 Announce Type: cross Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented cap
arXiv:2605.30346v1 Announce Type: new Abstract: As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistica
arXiv:2605.27725v1 Announce Type: cross Abstract: High-fidelity computational fluid dynamics (CFD) is widely used for thermal-fluid design, but repeated CFD solves remain expensive for design optimiza
arXiv:2605.28526v1 Announce Type: new Abstract: Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the
arXiv:2605.28174v1 Announce Type: cross Abstract: Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining
arXiv:2605.28816v1 Announce Type: new Abstract: World models for interactive video generation have largely focused on single-agent settings, where future observations are generated from a single contr
Organizations are unlocking entirely new ways to use image generation and editing across their industries. To drive next-generation experiences, businesses are embedding AI directly into creative, age
We're releasing Paris 2.0, which, to our knowledge, is the world's first decentralized trained video generation model. We benchmarked it against a monolithic model trained on the same data and compute
A closer look at what we released today 🧵 ESMC is a language model trained on billions of protein sequences spanning the full diversity of life. Trained across 2.8 billion sequences, the model is expo
arXiv:2009.11997v3 Announce Type: replace-cross Abstract: Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynam
arXiv:2605.26520v1 Announce Type: cross Abstract: While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow an
arXiv:2507.13762v4 Announce Type: replace Abstract: Motivation: Structure-based drug design (SBDD) has advanced with deep generative models, but bridging the gap between continuous atomic coordinates
arXiv:2603.07523v2 Announce Type: replace Abstract: Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a p
arXiv:2605.23934v1 Announce Type: new Abstract: Quantum computing devices are recognized as powerful tools for solving NP-complete problems. However, the intricacy of their modeling presents notable b
arXiv:2605.24852v1 Announce Type: new Abstract: Recent advances in learning-based model predictive control (MPC) have leveraged neural networks for online model learning, achieving strong performance
arXiv:2605.24411v1 Announce Type: new Abstract: Existing language model applications struggle to meet the demand for emotionally oriented support, primarily due to their inability to maintain deep, pe
arXiv:2605.24025v1 Announce Type: cross Abstract: Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly co
arXiv:2605.23790v1 Announce Type: new Abstract: Saliency prediction has been extensively studied in RGB images and videos as a computational model of human visual attention. In contrast, predicting sa
arXiv:2505.13893v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherit
arXiv:2605.22842v1 Announce Type: cross Abstract: Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumptio
arXiv:2601.21306v2 Announce Type: replace-cross Abstract: This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compoundin
arXiv:2506.04708v3 Announce Type: replace Abstract: Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree s
arXiv:2605.21728v1 Announce Type: cross Abstract: Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating
After 15 months of incremental updates, leaks, and rumored leaks, DeepSeek released version 4. It arrived without the fanfare R1 and R1-preview commanded in early 2025. That quiet reception is the mos
arXiv:2605.22089v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sp
arXiv:2605.20368v1 Announce Type: cross Abstract: Organizations that scan documents for sensitive information face a practical problem. Cloud services require data to be sent to external infrastructur
arXiv:2511.04106v5 Announce Type: replace-cross Abstract: The diffusion of ideas and language in society has conventionally been described by S-shaped models, such as the logistic curve. However, the
arXiv:2605.22417v1 Announce Type: new Abstract: We observe that existing model interpretation methods generally ignore the baseline, and such neglect often results in imprecise or even incorrect inter
arXiv:2602.05536v2 Announce Type: replace-cross Abstract: Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to r
arXiv:2501.02407v3 Announce Type: replace Abstract: Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant
arXiv:2512.00667v2 Announce Type: replace-cross Abstract: Effective medical simulators necessitate realistic haptic rendering of biological tissues that exhibit viscoelastic material properties, such
Did we ever learn what model won gold at the IMO from OpenAI? It was a year ago and it was called an unreleased internal general purpose model back then. Has GPT-5.5 Pro Extended caught up with whatev
arXiv:2602.23622v2 Announce Type: replace-cross Abstract: Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate pla
arXiv:2605.18803v1 Announce Type: cross Abstract: Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transiti
Also had some early access to Gemini 3.5 Flash. Very fast for a flash model and very capable, though not as powerful as a full frontier model. I added it to the gallery or procedurally generated one-s
Google AI announced Gemini Omni, a new multimodal model capable of generating diverse content types from various input formats, with initial focus on video generation capabilities. The model represent
Cerebras is now running Kimi K2.6 – a trillion parameter model – in enterprise trials. At ~1,000 tokens/s, this is the fastest frontier model performance ever measured by Artificial Analysis @Artifici
arXiv:2510.21712v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dyna
arXiv:2605.18383v1 Announce Type: new Abstract: We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. Tab
arXiv:2605.17575v1 Announce Type: cross Abstract: Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution s
arXiv:2510.22665v3 Announce Type: replace-cross Abstract: Synthetic Aperture Radar (SAR) is a critical imaging modality due to its all-weather operational capability. Although recent advances in self-
arXiv:2603.08063v3 Announce Type: replace Abstract: Cross-view UAV geolocalization is fundamentally a challenging large-scale image retrieval task, aiming to determine the geographic coordinates of Un
arXiv:2605.15733v1 Announce Type: cross Abstract: Humans abstract experiences into structured representations to facilitate pattern inference and knowledge transfer. While the hippocampal-entorhinal (
GLM-5.1 is a language model available through Ollama's model library, accessible via the Ollama platform for local deployment and use. The model can be pulled and run locally using Ollama's tools, mak
arXiv:2602.04289v2 Announce Type: replace Abstract: Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over U
arXiv:2605.14867v1 Announce Type: cross Abstract: Spike activity has been the dominant neural signal for behavior decoding due to its high spatial and temporal resolution. However, as brain-computer i
arXiv:2605.15178v1 Announce Type: new Abstract: We introduce SANA-WM, an efficient 2.6B-parameter open-source world model natively trained for one-minute generation, synthesizing high-fidelity, 720p,
arXiv:2605.13933v1 Announce Type: cross Abstract: Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis. This moti
arXiv:2602.05000v2 Announce Type: replace-cross Abstract: Reward guidance, also known as posterior sampling, is a popular method for test-time adaptation and post-training in continuous diffusion mode