Related papers: Proprio: Latent Self-Scoring and Inference-Time Re…
Proactive streaming video understanding requires models to continuously process video streams and decide when to respond, rather than merely what to respond. This naturally introduces a decision-making problem under partial observations,…
Physically Plausible Video Generation (PPVG) has emerged as a promising avenue for modeling real-world physical phenomena. PPVG requires an understanding of commonsense knowledge, which remains a challenge for video diffusion models.…
Recent advancements in video generation have witnessed significant progress, especially with the rapid advancement of diffusion models. Despite this, their deficiencies in physical cognition have gradually received widespread attention -…
Current motion-controlled image-to-video generation models rigidly follow user-provided trajectories that are often sparse, imprecise, and causally incomplete. Such reliance often yields unnatural or implausible outcomes, especially by…
Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are lossy…
Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level…
Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown that such pipelines suffer from severe temporal drift, where…
Foundation video models produce visually impressive results, but their use in embodied AI remains limited because they are primarily trained on natural language rather than low-level control signals. This limitation is especially pronounced…
Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension…
While generative models have become effective at producing human-like motions from text, transferring these motions to humanoid robots for physical execution remains challenging. Existing pipelines are often limited by retargeting, where…
We present PROGRESSOR, a novel framework that learns a task-agnostic reward function from videos, enabling policy training through goal-conditioned reinforcement learning (RL) without manual supervision. Underlying this reward is an…
The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future…
Recent advances in internet-scale video data pretraining have led to the development of text-to-video generative models that can create high-quality videos across a broad range of visual concepts, synthesize realistic motions and render…
Text-to-video diffusion models generate realistic videos, but often fail on prompts requiring fine-grained compositional understanding, such as relations between entities, attributes, actions, and motion directions. We hypothesize that…
Recent advancements in video generation models have significantly improved their ability to follow text prompts. However, the customization of dynamic visual effects, defined as temporally evolving and appearance-driven visual phenomena…
Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally…
Composed Video Retrieval (CoVR) aims to retrieve a video based on a query video and a modifying text. Current CoVR methods fail to fully exploit modern Vision-Language Models (VLMs), either using outdated architectures or requiring…
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and…
Recent advances in image-to-video (I2V) generation have achieved remarkable progress in synthesizing high-quality, temporally coherent videos from static images. Among all the applications of I2V, human-centric video generation includes a…
This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative models exhibit severely limited physical understanding, and…