Knowledge catalogue
arXiv:2607.02990v1 Announce Type: new Abstract: We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning nod
arXiv:2607.04648v1 Announce Type: cross Abstract: Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of inte
arXiv:2607.04153v1 Announce Type: cross Abstract: Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information. It is crucial to abstract effective state
arXiv:2607.02558v1 Announce Type: cross Abstract: As machine learning shifts from laboratory curiosity to critical infrastructure, the systems that sustain it span an extraordinary range, from sub-mil
arXiv:2607.05238v1 Announce Type: new Abstract: JEPA world models predict the next latent state with a single deterministic predictor trained by latent regression. We show that this fails structurally
arXiv:2607.03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind
arXiv:2601.07376v2 Announce Type: replace Abstract: We introduce extsc{OpenTinker}, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared exe
arXiv:2607.03425v1 Announce Type: new Abstract: Algorithmic recourse addresses the challenge of providing tailored recommendations to users affected by unfavorable machine learning decisions, in poten
arXiv:2405.07332v2 Announce Type: cross Abstract: Numerous applications have resulted from the automation of agricultural disease segmentation using deep learning techniques. However, when applied to
arXiv:2607.02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy conc
arXiv:2607.02881v1 Announce Type: new Abstract: Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelli
arXiv:2601.11049v2 Announce Type: replace-cross Abstract: We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions c
arXiv:2607.04846v1 Announce Type: cross Abstract: Transformers follow implicit curricula whereby some tasks are learned before others. However, how explicit pretraining curricula influence learning, g
arXiv:2607.04242v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has become an effective paradigm for improving large language model agents on long-horizon interactive tasks. To
arXiv:2607.02907v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but still struggle with complex visual reasoning tasks requiring multi-step
arXiv:2607.02932v1 Announce Type: cross Abstract: Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI
arXiv:2511.05730v2 Announce Type: replace Abstract: In this paper, a learning framework is introduced which incorporates principles of probabilistic inference, variational optimization, and geometry-p
arXiv:2607.04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constr
arXiv:2607.05007v1 Announce Type: new Abstract: This paper introduces a quantum-inspired computational framework for harmonic decision-making in music. The proposed approach formulates harmonization a
arXiv:2607.03502v1 Announce Type: cross Abstract: Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visi
arXiv:2607.05364v1 Announce Type: cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or inference-
arXiv:2607.03863v1 Announce Type: new Abstract: Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate problem
Sakana AI has launched a translation service that captures the nuanced 'tone and temperature' of Japanese expressions like '恐縮ですが' (apologetic) and 'それな' (casual agreement), going beyond literal trans
Sakana AI (@SakanaAILabs) is now a model vendor on Merge Gateway, and Fugu Ultra is live through them. It's a multi-agent orchestration model that routes across frontier models behind one API. You get
arXiv:2607.05382v1 Announce Type: cross Abstract: Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tai
arXiv:2607.04832v1 Announce Type: new Abstract: In recent years, studies have revealed a decline in semantic variety across popular music lyrics, particularly in English-language songs on streaming pl
arXiv:2607.04107v1 Announce Type: new Abstract: Word surprisal is a well-established computational predictor of human neural responses during language comprehension, but it remains less clear whether
arXiv:2607.04336v1 Announce Type: new Abstract: Modern video games are becoming more complex day by day. Most of these modern games are multiplayer first-person shooter (FPS) games. The rising popular
arXiv:2607.04261v1 Announce Type: new Abstract: Current Legal Judgment Prediction (LJP) is constrained by its reliance on post-hoc judicial materials, increasing the likelihood that models perform ret
arXiv:2601.08303v3 Announce Type: replace Abstract: Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to
arXiv:2607.05363v1 Announce Type: new Abstract: Personal agents are becoming persistent user-owned intermediaries: they remember preferences, filter platform-mediated information, use tools, and negot
arXiv:2606.20691v1 Announce Type: cross Abstract: Ontologies are useful structures to organize and maintain information that can be understood both by humans and systems. However, since their manual c
This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (des
arXiv:2607.05264v1 Announce Type: new Abstract: Existing video benchmarks evaluate action recognition on consumer videos, egocentric recordings, or simulated industrial environments. They do not test
arXiv:2607.03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, clo
The year 2026 could be remembered as the moment when storage technology received a massive promotion. The reason is that the current transition from simple chatbots to agentic AI systems has raised th
arXiv:2607.04378v1 Announce Type: new Abstract: Surgical automation is being increasingly studied, yet bridging visual scene understanding with autonomous action planning remains a fundamental challen
arXiv:2607.03236v1 Announce Type: new Abstract: Diffusion language models (DLLMs) generate text by iteratively denoising masked positions, exposing a trajectory of predictive distributions rather than
arXiv:2607.05001v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated an
This is what latency optimization looks like below the API 👇 Together ATLAS, NVIDIA Blackwell, CUDA, TensorRT-LLM, Dynamo, and custom kernels all working together to make inference faster for users. P
arXiv:2601.14192v2 Announce Type: replace Abstract: Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has conti
arXiv:2601.15235v4 Announce Type: replace-cross Abstract: Cervical spine fractures require rapid and accurate diagnosis, yet automatic CT interpretation remains challenging as subtle injuries must be
arXiv:2607.03210v1 Announce Type: cross Abstract: Standard machine learning training presents data as discrete endpoint pairs, omitting the structure of the space between them. This paper introduces T
arXiv:2603.03695v2 Announce Type: replace Abstract: Reliable localization is essential for sustainable forest management, as it allows robots to revisit and monitor the status of individual trees over
arXiv:2607.03176v1 Announce Type: new Abstract: Understanding how households consume electricity in response to socioeconomic and climatic drivers is important for decision-makers designing energy pol
arXiv:2607.05196v1 Announce Type: cross Abstract: Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A
arXiv:2607.05133v1 Announce Type: new Abstract: World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as den
arXiv:2607.04443v1 Announce Type: cross Abstract: We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 mod
arXiv:2607.04013v1 Announce Type: cross Abstract: Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling
arXiv:2607.03461v1 Announce Type: new Abstract: World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in
arXiv:2607.04945v1 Announce Type: new Abstract: LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically
arXiv:2607.05029v1 Announce Type: cross Abstract: Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage informati
Hy3, the new 295B MoE model from @TencentHunyuan, is now free in Nous Portal for the next two weeks! It is focused on cost-effective agentic use, and particularly strong on coding, tool-calling reliab
This article likely explores the concept of robustness in AI systems and what it means for AI to be 'robust to' various types of failures, adversarial inputs, or distribution shifts. The piece probabl
Reporting benchmark results as a single scalar percentage is insufficient for meaningful evaluation of model performance. Comprehensive benchmark reporting should include efficiency metrics alongside
In this post, we walk through how to get started with MiniMax models on Amazon Bedrock, including the capabilities supported by these models, the service tiers available, how on-demand inference scale
Sakana AI has launched 'Sakana Translate,' a free translation feature that preserves the tone and nuance of the original text, including formal language (keigo) and internet slang, supporting translat
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame
The automotive industry is at a pivotal crossroads as it hits the gas on adopting new technology. The era of the traditional connected vehicle has shifted into the age of the software-defined vehicle
tencent/Hy3 New Apache 2.0 licensed model from Tencent in China: Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tence