Latest AI/ML research from ArXiv and Papers with Code
Developing general-purpose algorithms with global asymptotic convergence guarantees for Nash equilibria of general-sum games remains a longstanding challenge. This paper extends th...
On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. However, existing approaches rely on ground-truth question-answer...
Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in...
Interactive video world models require coordinated control over viewing perspectives, character actions, and camera motion. Existing methods typically leave view modes implicit in ...
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However...
Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, ...
Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diverse successful demonstrations remains costly. We study reinfo...
Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabili...
Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such a...
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We pre...
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. Wi...
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: ...
Recent test-time training (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific di...
A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embo...
Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps. First, standard ben...
Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesi...
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is...
Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimodal models, and yet prevailing approaches based on pooling or...
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achi...
Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, act...
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view c...
Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific p...
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction require...
Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relation...