Knowledge catalogue
arXiv:2601.02918v3 Announce Type: replace Abstract: Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores withou
1 week left. This is your last chance to apply for the 72 Hour Video Hackathon. Build alongside the world's best creators and developers, get access to cutting-edge models, and compete for $150K in pr
arXiv:2607.06726v1 Announce Type: new Abstract: Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion fa
arXiv:2607.07527v1 Announce Type: cross Abstract: Artificial intelligence (AI) is a double-edged sword: while it has achieved remarkable success across a wide range of domains, its deployment also cal
arXiv:2607.06818v1 Announce Type: cross Abstract: For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality
arXiv:2607.07397v1 Announce Type: new Abstract: Autonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs. Th
arXiv:2607.07680v1 Announce Type: cross Abstract: Many machine learning models are defined for inputs of different sizes, such as point clouds containing different numbers of points, sequences of toke
Databricks' 5th Genie Hackathon demonstrated key insights about their Genie AI product through three core capabilities: asking questions about data, building analytical solutions, and composing workfl
arXiv:2504.01894v2 Announce Type: replace Abstract: We present a bifidelity method for uncertainty quantification of parameter estimates in complex systems, leveraging generative models trained to sam
arXiv:2607.07696v1 Announce Type: cross Abstract: Analytical workloads operating on data stored in external database systems face a fundamental bottleneck: data access is guarded entirely by the datab
arXiv:2411.17077v2 Announce Type: replace-cross Abstract: As Classifier-Free Guidance (CFG) has proven effective in conditional diffusion model sampling for improved condition alignment, many applicat
arXiv:2607.06609v1 Announce Type: cross Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep s
arXiv:2603.21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon t
arXiv:2607.06883v1 Announce Type: cross Abstract: We consider the problem of finding stationary points for stochastic convex optimization problems. Rather than surrogates to stationarity, such as a pr
arXiv:2603.17390v2 Announce Type: replace Abstract: Material classification has emerged as a critical task in computer vision and graphics, supporting the assignment of accurate material properties to
arXiv:2501.05711v4 Announce Type: replace Abstract: Vision Language Models (VLMs) have achieved strong performance across a wide range of video understanding tasks. However, their viewpoint-invariant
arXiv:2607.07141v1 Announce Type: new Abstract: Newly developed items must ordinarily be field tested before their psychometric properties are known, creating a cold start problem for item calibration
arXiv:2607.06833v1 Announce Type: new Abstract: Sampling stochastic signals supported on a graph underlies many graph machine learning tasks, including recommender systems, forecasting in financial ma
arXiv:2607.07494v1 Announce Type: cross Abstract: Gradient communication is a primary scaling bottleneck in large language model (LLM) pretraining. Communicating gradients in low-precision formats, su
Vercel has made GPT 5.6 models (Sol, Luna, and Terra variants) available through its AI Gateway service, expanding the model options developers can access and deploy through the platform. This update
arXiv:2607.06739v1 Announce Type: new Abstract: Event-based cameras are gaining popularity as the sensor of choice for mobile robotics, due to their high performance in dynamic environments. However,
arXiv:2604.25605v2 Announce Type: replace-cross Abstract: Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval
This IBM Research article examines how training environments and conditions can inadvertently cause AI models to develop undesirable behaviors or fail to learn intended objectives. The piece likely ex
arXiv:2304.03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural la
arXiv:2607.06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic
arXiv:2607.06845v1 Announce Type: new Abstract: African American English (AAE), a rule-governed dialect spoken by over 30 million people, is routinely misinterpreted and 'corrected' by large language
The Wishingrads are a family operating a cereal business from their home using GPT-5.6, likely demonstrating how advanced AI language models can assist small entrepreneurs and home-based businesses wi
Meta Platforms Inc. today launched a new flagship large language model optimized to power multi-agent automation workflows. Muse Spark 1.1 is available in the company’s Meta AI chatbot service and via
arXiv:2510.25370v2 Announce Type: replace Abstract: Forecasting transformative technologies remains a critical but challenging task, particularly in fast-evolving domains such as Information and Commu
arXiv:2607.07304v1 Announce Type: new Abstract: In this paper we first study the problem of generalized linear bandit (GLB) under heavy-tailed noise. The characteristics of heavy-tailed distributions
OpenAI Group PBC today launched a new “agentic” tool called ChatGPT Work as it announced the global rollout of its most advanced model family so far in GPT-5.6. ChatGPT Work is a new mode within ChatG
OpenAI released ChatGPT Work, a general-purpose productivity agent designed to help people with ambitious tasks beyond traditional coding projects. The tool performs actions autonomously across connec
arXiv:2601.20226v2 Announce Type: replace Abstract: We propose two methodologies for modelling aggregated supply and demand curves in the EPEX SPOT Dayhar45 Ahead market, emphasizing generative models
arXiv:2607.07634v1 Announce Type: cross Abstract: Time series analysis plays a vital role across a wide range of scientific and engineering domains but poses substantial computational challenges. A ma
arXiv:2607.06843v1 Announce Type: new Abstract: Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temp
arXiv:2607.06979v1 Announce Type: new Abstract: Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refr
arXiv:2603.00233v2 Announce Type: replace-cross Abstract: Quantum generative modeling is a rapidly evolving discipline at the intersection of quantum computing and machine learning. Contemporary quant
arXiv:2607.06948v1 Announce Type: cross Abstract: The accuracy of existing leaf-wood segmentation methods for tree point clouds varies across forest types and sites. Self-supervised learning (SSL) on
SensorFM is a foundation model that analyzes multimodal wearable sensor signals from devices like smartwatches and fitness trackers to generate insights into health and activities. The model was train
arXiv:2607.06748v1 Announce Type: cross Abstract: Smart home automation platforms increasingly rely on user-authored YAML configuration files to define device behaviors, but these files are prone to s
arXiv:2511.18735v3 Announce Type: replace-cross Abstract: In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applicatio
arXiv:2607.06875v1 Announce Type: new Abstract: Understanding and forecasting audience reactions to video content are crucial for improving content creation, recommendation systems, and media analysis
We are nearing 1,000 signups for the first-ever global video hackathon taking place next weekend. We are also opening a new track: VIDEO APPS. What new apps can you make w/ gen video? Filmmakers, deve
arXiv:2607.07216v1 Announce Type: new Abstract: Deepfake (DF) technology poses a significant threat to information integrity, driving the need for robust detection methods. Most DF detectors only cons
arXiv:2607.06252v1 Announce Type: cross Abstract: Many problems in science and engineering are difficult to model accurately, either due to unknown physical mechanisms, poorly quantified measurement u
arXiv:2607.06479v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while embedding the underlying physica
arXiv:2602.13213v2 Announce Type: replace Abstract: Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine p
arXiv:2607.05614v1 Announce Type: cross Abstract: Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in r
arXiv:2607.05445v1 Announce Type: cross Abstract: Extended Reality (XR) wearables require always-on perception within tight power envelopes of a few watts and motion-to-photon latency budgets below 20
arXiv:2511.16137v2 Announce Type: replace Abstract: Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enh
arXiv:2607.05428v1 Announce Type: cross Abstract: We present Charlie, an on-premise multi-agent Retrieval-Augmented Generation (RAG) system for structured evidential processing in digital forensic env
Vercel has announced support for Vercel Connect within its Chat SDK, enabling developers to integrate real-time chat functionality with Vercel's infrastructure and deployment services. This update lik
arXiv:2607.06499v1 Announce Type: new Abstract: With the widespread availability of parallel computing hardware, sampling-based motion planning methods such as Model Predictive Path Integral (MPPI) co
Come help us scale @harvey’s model training team. If you’re interested in bringing frontier agent research into the Harvey product and working with: - @baseten to scale up RL to 80M+ token virtual dat
LlamaIndex is inviting users to process large-scale document collections through its cloud platform at cloud.llamaindex.ai. The post, from LlamaIndex founder Jerry Liu, highlights the platform's capab
arXiv:2505.10356v3 Announce Type: replace Abstract: Decoding language from the human brain remains a grand challenge for Brain-Computer Interfaces (BCIs). Current approaches typically rely on unimodal
arXiv:2607.05957v1 Announce Type: new Abstract: Multi-agent active visual triangulation enables precise 3D localization of aerial targets by coordinating mobile observers with controllable cameras. Ho
arXiv:2607.06320v1 Announce Type: cross Abstract: We present the dithered Gaussian mechanism, a novel alternative to the discrete Gaussian mechanism for differential privacy that discretizes the priva
arXiv:2607.05644v1 Announce Type: cross Abstract: Natural language processing (NLP) is a common method for supplying data to clinical research and decision making by extracting information from electr
arXiv:2607.06150v1 Announce Type: new Abstract: Reliable seam segmentation is essential for autonomous robotic welding in construction, where harsh illumination, specular reflections, and thin weld ge