Latest AI/ML research from ArXiv and Papers with Code
Generating complete, coherent, and usable 3D indoor scenes from natural language requires strong design intelligence: the ability to design high-quality scenes and critique their q...
AI agents increasingly use files and software tools to produce professional deliverables. Such work draws on materials, decisions, and feedback accumulated across assignments. We i...
Open-ended search combined with foundation models has produced advances such as faster algorithms, new results on open mathematical problems, and self-improving agents. We extend t...
Language models are increasingly trained against several verifiable rewards at once, such as the correctness and the format of a tool call, or the individual constraints of a compl...
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leav...
Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question answering. Existing self-impro...
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the qua...
Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribut...
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech to...
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) fore...
Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a cont...
Dynamic Gaussian representations have made high-quality, real-time volumetric video increasingly practical, yet challenging motion can still break their reconstruction: small fast-...
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with complex, c...
Text-based world models have recently shown potential to simulate complex RL environment state transitions for a diverse set of use cases. However, no standardized benchmark exists...
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associat...
Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verif...
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view d...
GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks ...
Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and system st...
ARTIFICIAL INTELLIGENCE (AI) has demonstrated its potential across a wide range of humanitarian tasks, offering scalable and data-driven solutions to some of the world's most press...
While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently l...
Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routi...
Recent advances in Omni Language Models (OLMs) provide a unified solution for audiovisual video captioning. Nevertheless, existing approaches predominantly treat captioning as an u...
Reinforcement learning (RL) can elicit specialized visual capabilities in vision-language models (VLMs), yet jointly optimizing heterogeneous objectives often introduces cross-capa...