arXiv:2511.02258v3 Announce Type: replace Abstract: This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD). Building on the work of Ben Arous, Gheissari,…
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into…
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In…
We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its…
Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-token importance ratio for…
Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for…
The development of generalizable robotic manipulation policies is inherently bounded by the availability of large-scale, high-fidelity scene data. While recent automated synthesis methods attempt to bridge…
Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video…
The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are…
Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true,…
Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native…
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often underexplored.…
Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, reduced contrast,…
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows.…
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although…
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued…
Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it. The test is structurally…
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-p routing…
Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the lack of training data that…
Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works…
Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its own rollout rather than ground-truth…
arXiv:2607.19354v1 Announce Type: new Abstract: Spreadsheet applications are used by hundreds of millions worldwide, yet writing formulas remains a significant barrier. Existing approaches rely on static…
arXiv:2602.16161v4 Announce Type: replace-cross Abstract: Emotional expression underpins natural communication and effective human-computer interaction. We present Emotion Collider (EC-Net), a hyperbolic hypergraph framework for multimodal emotion…
arXiv:2607.19747v1 Announce Type: new Abstract: As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound…