arXiv:2607.08252v1 Announce Type: cross Abstract: Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions. We identify self-locking as a…
arXiv:2607.08010v1 Announce Type: new Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace…
arXiv:2607.07962v1 Announce Type: new Abstract: Inferring latent physical properties from sensory observations is a fundamental challenge in machine perception. Among available sensing modalities, thermal imaging is…
arXiv:2603.00910v2 Announce Type: replace-cross Abstract: Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant.…
arXiv:2607.08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all…
arXiv:2604.11305v3 Announce Type: replace-cross Abstract: Conformal selection (CS) uses calibration data to identify test inputs whose unobserved outcomes are likely to satisfy a pre-specified minimal quality…
arXiv:2512.13997v2 Announce Type: replace Abstract: Existing two-sample testing techniques, particularly those based on choosing a kernel for the Maximum Mean Discrepancy (MMD), often assume equal sample…
Reinforcement learning (RL) has become the standard paradigm for enhancing the complex reasoning capabilities of large language models (LLMs). To achieve sample efficiency, modern RL frameworks…
We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through…
Inference-time scaling for text-to-image generation has progressed from simple Best-of-N (BoN) sampling to guided search methods that verify and steer candidate trajectories at intermediate denoising steps.…
Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise…
Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose accumulated reasoning and tool traces routinely push the…
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks…
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct…
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low…
Pretrained video generative models are promising backbones for visuomotor control, but their imagined futures often drift from task intent and are not reliably action-conditional. As a…
Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to spend a pretraining…
Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success significantly depends on local…
Accurate breast cancer classification from mammography requires effective integration of complementary information from craniocaudal (CC) and mediolateral oblique (MLO) views, which provide a more complete characterization…
We present AgentLens, a production-assessed benchmark for interactive code agents. Most code-agent benchmarks reduce a run to a single bit -- did the task pass? --…
Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping…
Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient…
Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limited state size, linear attention models…
Long-horizon failure in world models is conventionally attributed to compounding error, a generic framing that does not distinguish what kind of error compounds. We propose a…