Knowledge catalogue
arXiv:2607.00606v1 Announce Type: new Abstract: Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesi
arXiv:2607.01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generat
arXiv:2511.18011v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine
arXiv:2607.00856v1 Announce Type: cross Abstract: In recent years, large language models have achieved remarkable success and have seen growing adoption in financial applications. At the same time, ex
arXiv:2607.00774v1 Announce Type: new Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models.
arXiv:2511.19985v3 Announce Type: replace Abstract: We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic
arXiv:2607.00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue re
arXiv:2607.01204v1 Announce Type: new Abstract: We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both p
arXiv:2607.01133v1 Announce Type: new Abstract: Accurate trajectory forecasting of surrounding traffic participants is a core capability for autonomous driving, enabling vehicles to anticipate behavio
arXiv:2607.00913v1 Announce Type: new Abstract: As exponential compute scaling continues, will the capabilities of frontier AI models outstrip what is accessible to developers on a small fixed budget?
arXiv:2503.13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful,
arXiv:2606.32007v1 Announce Type: new Abstract: We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification. We present AxDafny
arXiv:2606.31861v1 Announce Type: cross Abstract: Dynamic epistemic logic represents belief change via model transformations induced by epistemic events. Its standard formulation (Baltag, Moss, Soleck
arXiv:2606.31002v1 Announce Type: new Abstract: Theorem-proving benchmarks evaluate proof search against fixed formal statements, but natural-language-to-Lean formalization must generate the formal st
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede the exchange of research results between these co
arXiv:2606.31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned
arXiv:2606.30651v1 Announce Type: cross Abstract: Delirium is common in hospitalized patients and is often missed in routine care. We present a user-centered interactive machine learning (UC-iML) fram
Vercel has restored access to Claude Fable 5 on its AI Gateway service, allowing developers to integrate the model into their applications through Vercel's platform. This restoration enables continued
arXiv:2606.31461v1 Announce Type: new Abstract: Niche asset markets, such as Counter-Strike 2 (CS2) weapon skins, are small, volatile, and heavily driven by community discussions and platform rules. T
arXiv:2508.01273v3 Announce Type: replace Abstract: Explicit knowledge conflicts, occurring when retrieved contexts contain contradictory information, pose a fundamental challenge for Large Language M
arXiv:2606.20196v2 Announce Type: replace Abstract: Continual Test-Time Adaptation (CTTA) aims to maintain model performance under evolving target domains by adapting online without labeled data. Howe
arXiv:2606.31015v1 Announce Type: new Abstract: Transformer-based approaches have obtained excellent performance in multispectral object detection tasks due to their ability to model long-range depend
arXiv:2606.31092v1 Announce Type: new Abstract: Full fine-tuning adapts large language models to new tasks but can erode capabilities they already possess. Existing remedies protect through proxies su
arXiv:2606.31226v1 Announce Type: new Abstract: World-model-based autonomous driving endows the model with the ability to understand scene evolution. Yet this promise is undermined by the prevailing i
Gemini 2 Flash, Google's multimodal AI model, enables video editing capabilities including object swapping, environment changes, and targeted edits through simple text prompts. The feature allows user
Gemini Omni Flash is a model capability that generates video content from still images, likely integrated into or demonstrated through ComfyUI's node-based interface. This feature represents advanceme
Gemini Omni Flash: Video Edit is a ComfyUI workflow or tool that enables video editing capabilities using Google's Gemini Omni Flash model, likely allowing users to perform AI-assisted video editing t
Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX! The speedup comes from improved multi-token prediction (MTP), now on by default for Gemma 4, with more models to come. Ollama a
arXiv:2606.31813v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) and its variants enable parameter-efficient fine-tuning of large language models under the supervised fine-tuning (SFT) par
arXiv:2601.08187v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding. Recent studies typically focus o
arXiv:2606.31115v1 Announce Type: new Abstract: Generating realistic human avatars in complex motions--such as clothing dynamics--requires modeling of global and local deformations which remains chall
arXiv:2606.23375v2 Announce Type: replace-cross Abstract: While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow u
arXiv:2606.31167v1 Announce Type: cross Abstract: VLA models have emerged as a powerful paradigm for transferring semantic knowledge from web-scale data to physical robotic control. However, current s
arXiv:2606.30995v1 Announce Type: new Abstract: Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For
arXiv:2606.31073v1 Announce Type: new Abstract: Large language models (LLMs) provide a promising interface for high-level robotic task planning, but their use in multi-UAV collaboration remains diffic
arXiv:2606.31388v1 Announce Type: new Abstract: We introduce extbf{OVOW}, the first training-free system that reconstructs instance-level, simulation-ready 4D mesh scenes from a single monocular video
arXiv:2409.10141v3 Announce Type: replace Abstract: Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress. However, full-body reconstruct
This post from Ollama's official X account discusses performance improvements for the Gemma 4 model, likely covering optimizations related to MLX (Machine Learning eXperimental framework) and MTP (Mul
arXiv:2603.13057v2 Announce Type: replace Abstract: As virtual try-on (VTON) systems become increasingly important in fashion e-commerce, there is a growing need for reliable reference-free evaluation
arXiv:2606.31249v1 Announce Type: new Abstract: In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge wit
arXiv:2606.31446v1 Announce Type: new Abstract: RVL-CDIP is a popular dataset for benchmarking document classifiers. However, the dataset contains ample amounts of label errors as well as non-trivial
arXiv:2606.31248v1 Announce Type: cross Abstract: Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate t
arXiv:2606.30783v1 Announce Type: cross Abstract: We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppres
arXiv:2606.31732v1 Announce Type: new Abstract: Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise al
We are SO back Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to
arXiv:2606.31112v1 Announce Type: new Abstract: ASR systems have been often reported to underperform on atypical speech. An often conflated compounding factor is the existence of two valid transcripti
arXiv:2606.30815v1 Announce Type: cross Abstract: Recent work suggests that transformer language models show a bias towards human languages over unnatural ('impossible') languages argued to be unacqui
arXiv:2606.29516v1 Announce Type: new Abstract: A central challenge in statistical modeling is identifying the subset of features that belong in the true regression model. The classical best subset se
arXiv:2410.24050v3 Announce Type: replace Abstract: Large-scale pretraining of transformers has been central to the success of foundation models. However, the scale of those models limits our understa
arXiv:2601.11473v2 Announce Type: replace-cross Abstract: We present a novel probabilistic approach for optimal experimental path design. In this approach a discrete path optimization problem is defin
arXiv:2606.28733v1 Announce Type: new Abstract: LLM agents are expected to act over multiple turns, using search, browsing interfaces, and terminal tools to complete user goals. Yet not every goal is
Ahmad Osman discusses the technological and practical reasons why locally-run AI models are becoming increasingly competitive with cloud-based alternatives, likely covering improvements in model effic
arXiv:2606.28593v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) have achieved significant improvements on static visual-to-code tasks such as generating code for webpages,
arXiv:2603.10438v2 Announce Type: replace-cross Abstract: Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational co
arXiv:2606.29184v1 Announce Type: new Abstract: While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid desi
arXiv:2606.28963v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to simulate social survey responses, yet their outputs exhibit systematic biases: marginal distributi
arXiv:2606.30044v1 Announce Type: new Abstract: A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models b
arXiv:2606.29416v1 Announce Type: cross Abstract: Can a vision model truly see an object, or does it only fit surface-level visual cues? Following Wittgenstein's view that the limits of language are t
Claude Sonnet 5 is now available as a model option in the Cursor code editor. On CursorBench, Sonnet 5 achieves a 57% score compared to Sonnet 4.6's 49%, representing a meaningful performance improvem
arXiv:2606.28533v1 Announce Type: cross Abstract: Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) b