Latest AI/ML research from ArXiv and Papers with Code
Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase training ...
We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse environments with simulated comme...
Whole-slide images (WSIs) are gigapixel-scale digital scans of histopathology tissue and serve as the primary basis for cancer diagnosis. Existing histopathology generative models ...
Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-perceiving them for action s...
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by...
Large language models (LLMs) are increasingly explored for graph understanding and decision-making, while System One models such as Jev select directly from supplied options. Howev...
Visual representations are largely developed for understanding, yet what makes them useful for generation remains unclear. We study this question in pixel diffusion transformers an...
Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinfo...
Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as inference becomes a dominant compu...
On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantial...
Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when...
Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, existing work remains largely con...
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent fe...
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unrel...
Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users to specify handle and target points. Existing methods have ma...
Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this ...
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a giv...
Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-traini...
Augmenting worker capabilities in the physical world through guidance has been a decades-long goal for AI agents. One key supporting capability is to understand what the worker is ...
Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal. Training them via reinforcement learning (RL) requires diverse and ...
Decoder hidden states from different layers of large language models (LLMs) often encode complementary information. However, existing speculative decoding methods typically rely on...
The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces ...
Automatic speech recognition produces words but drops the non-verbal content of a recording: the breaths, coughs, sighs and laughter of the speaker, and the horns, music or barking...
We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their W...