A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently …

Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing b…

Code world models represent worlds as executable programs, but this representation alone does not determine how to const…

Optical flow methods typically rely on task-specific inductive biases, such as correlation volumes, feature warping, and…

Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digit…

Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous sy…

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally bli…

Mainstream robotic policies often adopt a Markovian formulation, but many complex real-world manipulation tasks are inhe…

Autoregressive video world models enable interactive, long-horizon exploration, but flexible control remains challenging…

On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement, al…

All-in-One medical image restoration (MedIR) aims to address diverse tasks across modalities and degradation types using…

Late-interaction retrieval is the state-of-the-art for visual document search, but it pays for its accuracy in storage. …

Agent usage is shifting toward long-horizon tasks such as coding and scientific discovery, among which terminal tasks ar…

We launch SenseNova-U1.5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visua…

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence i…

We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a transit kiosk. It…

Recent video world models generate increasingly realistic and interactive visual experiences, yet lack reliable mechanis…

We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining beyond standard next-…

Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain ov…

We study how model post-training and test-time inference design affect natural-language proof generation for hard olympi…

Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine…

Existing emotional support conversation systems mainly focus on one-on-one seeker-supporter interactions and individual …

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentia…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on…

Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video repres…

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the pro…

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…

In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic cap…

We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design …

Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …

Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in sc…

The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet ful…

Leading benchmarks for formal theorem proving with large language models are small collections drawn from competition ma…

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a …

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sideste…

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…

Image tokenizers define the ``visual language'' of unified multimodal models, yet are commonly studied through isolated …

World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-…

Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. …

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how schemi…

Large language model (LLM)-based multi-agent systems (MAS) achieve strong performance by employing specialized multiple …

As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identif…

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used t…

SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-l…

Autoregressive (AR) video diffusion models have shown great potential in real-time video generation. Recent methods dist…

We consider the problem of support recovery for sparse binary signals from noisy linear measurements. For sparse Gaussia…

We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that…

Accurate estimation of clinically meaningful gait parameters from monocular video is important for scalable mobility ass…

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autono…