arXiv:2602.17817v1 Announce Type: new Abstract: Collocating deep learning training tasks improves GPU utilization but causes drastic slowdowns due to resource contention and risks Out-of-Memory (OOM) failures. Accurate memory estimation is essential for robust collocation, while GPU utilization — a key proxy for resource contention — enables interference-aware scheduling to reduce slowdowns and improve throughput. Existing GPU memory estimators span three paradigms — analytical models, CPU-side libraries, and ML-based estimators — each with distinct limitations: dependence on detailed model […]

Ver mais

arXiv:2604.09686v1 Announce Type: new Abstract: Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action (VLA) models introduce common-sense reasoning through large-scale multimodal pretraining, enabling zero-shot performance across tasks. However, these models still lack explicit mechanisms to represent and update belief, limiting their ability to reason like humans or capture the evolving human intent over […]

Ver mais

Building used to be the bottleneck. Now it’s everything that comes after. Image sourced from Abhiram Kakarla’s LinkedIn You ship a working product in twelve hours. Auth, payments, a clean dashboard, even some halfway-decent onboarding copy. The model keeps up, you keep prompting, and somewhere around hour ten you start feeling that specific kind of high — the one where you’re convinced this is the thing. You post the link. You lean back. You wait. Three days later, your only signups are you, […]

Ver mais

arXiv:2603.28774v1 Announce Type: new Abstract: This demo introduces Focus360, a system designed to enhance user engagement in 360{deg} VR videos by guiding attention to key elements within the scene. Using natural language descriptions, the system identifies important elements and applies a combination of visual effects to guide attention seamlessly. At the demonstration venue, participants can experience a 360{deg} Safari Tour, showcasing the system’s ability to improve user focus while maintaining an immersive experience.

Ver mais

The internet used to reward speed. Then it rewarded scale. Now it rewards automation. And that is exactly why being human is starting to matter more than ever. For years, the web has been moving toward frictionless everything. Faster signups. Faster payments. Faster content creation. Faster customer support. Faster growth. Every platform wanted to remove steps, cut waiting time, and make interaction feel instant. Convenience became the product. Smoothness became the selling point. But the internet of 2026 […]

Ver mais

We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon’s multi-agent battle system and expansive role-playing game (RPG) environment. Partial observability, game-theoretic reasoning, and long-horizon planning remain open problems for frontier AI, yet few benchmarks stress all three simultaneously under realistic conditions. PokeAgent targets these limitations at scale through two complementary tracks: our Battling Track, which calls for strategic reasoning and generalization under partial observability in competitive Pokemon battles, and our Speedrunning Track, which […]

Ver mais

Self-supervised learning (SSL) is a powerful paradigm for learning from unlabeled time-series data. However, popular methods such as masked autoencoders (MAEs) rely on reconstructing inputs from a fixed, predetermined masking ratio. Instead of this static design, we propose treating the corruption level as a new degree of freedom for representation learning, enhancing flexibility and performance. To achieve this, we introduce the Flow-Guided Neural Operator (FGNO), a novel framework combining operator learning with flow matching for SSL training. FGNO […]

Ver mais

arXiv:2602.15864v1 Announce Type: new Abstract: Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations, which restrict global foresight and lead to inefficient exploration. In contrast, humans plan using maps: we reason globally first, then act locally. We introduce ReasonNavi, a human-inspired framework that operationalizes this reason-then-act paradigm by coupling Multimodal Large Language Models (MLLMs) with deterministic planners. ReasonNavi converts a top-down map into a discrete reasoning space by room segmentation and candidate […]

Ver mais

Notice anything special about the following sequence? 8 6 10 3 1 11 1 3 6 8 12 9 7 10 4 2 5 11 2 4 7 9 5 12 Each of the numbers 1 through 12 appear twice. Between the two 1s there is one number. Between the two 2s there are two numbers. Between the two 3s there are three numbers, etc. Langford’s problem of order n is to arrange two copies of the integers 1 […]

Ver mais

arXiv:2602.15984v1 Announce Type: new Abstract: Flow and diffusion models are typically pre-trained on limited available data (e.g., molecular samples), covering only a fraction of the valid design space (e.g., the full molecular space). As a consequence, they tend to generate samples from only a narrow portion of the feasible domain. This is a fundamental limitation for scientific discovery applications, where one typically aims to sample valid designs beyond the available data distribution. To this end, we address the […]

Ver mais