Learning-to-Defer with Expert-Conditional Advice
arXiv:2603.14324v3 Announce Type: replace-cross Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert
Knowledge catalogue
arXiv:2603.14324v3 Announce Type: replace-cross Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert
arXiv:2605.20780v1 Announce Type: cross Abstract: Physics-informed diffusion models typically enforce PDE constraints only on final outputs, leaving intermediate representations unconstrained and pron
arXiv:2605.20667v1 Announce Type: new Abstract: Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and
arXiv:2605.20314v1 Announce Type: new Abstract: This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a large
arXiv:2605.21280v1 Announce Type: new Abstract: High-fidelity EEG generation is critical for alleviating data scarcity and addressing privacy constraints in large-scale neural modeling. Despite recent
arXiv:2510.09060v2 Announce Type: replace-cross Abstract: Flow-based text-to-image models follow deterministic trajectories, making it costly to explore diverse modes under limited sampling budgets. E
arXiv:2605.20192v1 Announce Type: new Abstract: Decentraland, a decentralized virtual reality platform operating within the expanding Metaverse ecosystem, utilizes its native MANA token to facilitate
arXiv:2605.21465v1 Announce Type: new Abstract: In model-driven engineering, metamodel evolution leads to the need to adapt corresponding grammars to maintain consistency, which typically requires ted
arXiv:2605.20211v1 Announce Type: new Abstract: Educational videos are a cornerstone of remote and blended learning. However, learners' fluctuating attention remains a significant barrier to effective
The mission begins now. GeForce NOW is dialing up the action with a blockbuster mix of spy thrills, high-speed racing and member rewards — plus eight new games joining the cloud this week, all ready t
arXiv:2605.20436v1 Announce Type: new Abstract: Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world
arXiv:2605.21123v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are co
LoRA models can be used with image-to-video workflows to create automatic lip-syncing effects by controlling camera movements and instructing the model to synchronize audio with mouth movements. This
LxMLS 2026 is a 6-day in-person event scheduled for July 20-25 at Instituto Superior Técnico that covers machine learning topics from theory to practice for solving natural language processing problem
arXiv:2605.06139v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize r
arXiv:2605.21007v1 Announce Type: new Abstract: Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time in
arXiv:2605.20706v1 Announce Type: cross Abstract: Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contendin
arXiv:2605.20449v1 Announce Type: new Abstract: Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because
LLM training is built on fast MatMuls. But many surrounding ops still run as memory-bound kernels. CODA reparameterizes them to hide in the matmul’s shadow, fused into its epilogue before results leav
arXiv:2502.12120v3 Announce Type: replace-cross Abstract: Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and co
arXiv:2605.21251v1 Announce Type: cross Abstract: A retinal vessel analysis is a procedure that can be used as an assessment of risks to the eye. This work proposes an unsupervised multimodal approach
arXiv:2605.21086v1 Announce Type: new Abstract: While Large Language Models (LLMs) are increasingly integrated into in-vehicle conversational systems, identifying the optimal model remains challenging
Robert Booth / The Guardian: London Mayor Sadiq Khan blocks the Met police's £50M Palantir deal to automate intelligence analysis, citing a “clear and serious breach” of procurement rules — Exclusive:
arXiv:2605.20201v1 Announce Type: new Abstract: Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Su
longer comment on yesterday’s stories the nuance between yesterday’s stories that X influencers won’t tell you: https://open.substack.com/pub/garymarcus/p/checking-the-math-behind-openai-and?r=8tdk6&u
arXiv:2605.20866v1 Announce Type: new Abstract: Communication is a major bottleneck in distributed learning, especially in large-scale settings and in federated learning environments with slow links.
arXiv:2605.21446v1 Announce Type: new Abstract: Interpretable autonomous driving planners depend not only on generating explanations, but also on those explanations remaining reliable under real-world
arXiv:2605.20735v1 Announce Type: new Abstract: This paper proposes two new open-source iris recognition algorithms, providing both Python and IREX-compliant C++ implementations to be submitted to the
arXiv:2605.20670v1 Announce Type: new Abstract: Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pair
LTX-2.3 is a multimodal video generation model developed by Lightricks that generates synchronized audio and video in a single forward pass at resolutions up to 4K at 50 frames per second. The model i
arXiv:2507.06929v2 Announce Type: replace-cross Abstract: We investigate Machine-Learned Force Fields (MLFFs) trained on approximate Density Functional Theory (DFT) and Coupled Cluster (CC) level pote
arXiv:2605.20523v1 Announce Type: new Abstract: Advanced fibrosis is a major determinant of liver-related morbidity in metabolic dysfunction-associated steatotic liver disease (MASLD). FIB-4 is widely
arXiv:2605.20240v1 Announce Type: new Abstract: Battery health diagnostics today rely overwhelmingly on electrochemical signals measured at the cell terminals. A parallel literature has shown that mag
MagenticLite is an agentic system for small models that works across the browser and local file system in a single workflow. It combines specialized models and orchestration to support efficient agent
arXiv:2605.20577v1 Announce Type: cross Abstract: Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes presen
Even as AI rewrites the rules across industries, healthcare is still confronting a half-century of diagnostic stasis — but a new generation of companies is betting that advances in AI and 3D medical i
Managed Deep Agents is a new LangChain feature in private beta that provides managed infrastructure for deep agents, designed to be model-agnostic and deployable with minimal code. The service aims to
arXiv:2605.21182v1 Announce Type: new Abstract: Manga is a culturally distinctive multimodal medium and one of the most influential forms of Japanese popular culture. As AI systems increasingly target
arXiv:2605.20889v1 Announce Type: new Abstract: Monocular egocentric human pose estimation is essential for ubiquitous activity monitoring. However, understanding the user's absolute location within t
arXiv:2605.20549v1 Announce Type: new Abstract: Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive t
Marc Andreessen (@pmarca) on what it’s like to work at SpaceX: “It’s like being dropped into a zone of shocking competence.” “Everybody is ultra competent, and the reason everybody’s ultra competent i
arXiv:2605.20824v1 Announce Type: new Abstract: Many sequence computations are easier to study as movement through internal states than as isolated local circuits. We introduce Markovian Circuit Traci
arXiv:2603.06007v2 Announce Type: replace Abstract: Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and
Math is easy* because it has verifiable outputs and few messy judgement choices to make. Which AI labs have the guts to make advancing social science a priority? It may actually do more for human flou
arXiv:2605.20612v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-unders
arXiv:2511.21223v2 Announce Type: replace-cross Abstract: Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models. However, its formul
Elon Musk posted an aspirational message expressing hope that the current period represents a transformative new beginning for humanity. The post reflects optimistic sentiment about future progress an
arXiv:2605.21406v1 Announce Type: new Abstract: We present MC-Risk, a planner-aligned, multi-component risk field on a bird's-eye-view grid that yields early, calibrated, and class-aware risk localiza
arXiv:2509.08010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) distinguish themselves from previous technologies by functioning as collaborative ``thought partners,'' capable o
arXiv:2605.20410v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases.
arXiv:2605.20299v1 Announce Type: new Abstract: Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to
arXiv:2605.20607v1 Announce Type: cross Abstract: EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural netwo
arXiv:2605.20297v1 Announce Type: new Abstract: Medical image segmentation faces a fundamental challenge in continual learning: data arrives sequentially from heterogeneous sources, yet effective cont
arXiv:2605.20197v1 Announce Type: new Abstract: Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaningful c
📣Meet Qwen3.7-Max — our latest flagship, made for the Agent Era. A versatile foundation for agents that actually get things done: 🧑💻 Coding agent, end to end. Frontend prototypes, multi-file refactor
arXiv:2605.21463v1 Announce Type: new Abstract: We present Mem-pi, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrie
arXiv:2605.20833v1 Announce Type: new Abstract: Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of person
arXiv:2605.21402v1 Announce Type: cross Abstract: Generative neural networks learn how to produce highly realistic images from a large, but finite number of examples - or do they simply memorise their
arXiv:2605.20723v1 Announce Type: new Abstract: Deploying large deep neural networks on memory-constrained mobile devices is a central challenge in edge ML. While compression, pruning, and quantizatio
arXiv:2605.20948v1 Announce Type: new Abstract: Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables fro