On-policy distillation (OPD) has become an important approach to language model post-training. However, despite its performance gains, OPD can also collapse into excessively long a...
Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstrations remains expensive and difficult to scale. Egocentric v...
Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausi...
Chain-of-thought (CoT) reasoning allows humans to inspect how large language models reach their answers, and oversee model behaviour. This reasoning comes at an increased inference...
Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical numerical observations insuffi...
We reconstruct high-fidelity 3D scene meshes from posed multi-view images without per-scene optimization, across scales ranging from single objects to large outdoor scenes. Per-sce...
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can still violate real-world plausib...
Terminal agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference beh...
Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. However, exis...
Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial tok...
Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable fa...
Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benc...
Extending a text embedding model to new modalities typically degrades text retrieval quality, and existing omni-modal embedders compensate with multi-billion parameters. We present...
Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier att...
Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software sta...
Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate representation decodable for the sa...
Looped Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared Transformer blocks, they increase effective depth without increasing par...
Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scientific literature co-evolve. As ...
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improving from its own attemp...
In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. Me...
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored. We...
Recent years have seen the employment of a plethora of machine learning (ML) models in high-stakes domains, but they remain largely opaque to the practitioners who act on their pre...
Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biological text. Their benchmark accuracy is taken as evidence that...
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruc...