10 papers
IsoVRBench: Video Reward Modeling Without Human Feedback
Shuyue Stella Li, Jacqueline He, Jiahui Chen +5
Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignment, visual fidelity, motion,…
ExploreNet: Learning Where to Explore in Diffusion GRPO
Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1
Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This noise decides which rollouts…
Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts
Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1
Precise instruction following in image generation, such as satisfying object counts and spatial relations, remains an open challenge at least in part because it is learned using un…
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
Nicolas Beltran-Velez, Felix Friedrich, Zhang Xiaofeng +4
Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering propertie…
Fast Byte Latent Transformer
Julie Kallini, Artidoro Pagnoni, Tomasz Limisiewicz +5
Recent byte-level language models (LMs) match the performance of token-level models without relying on subword vocabularies, yet their utility is limited by slow, byte-by-byte auto…
Inference-time Physics Alignment of Video Generative Models with Latent World Models
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency t…
Unified Text-Image Generation with Weakness-Targeted Post-Training
Jiahui Chen, Philippe Hansen-Estruch, Xiaochuang Han +7
Unified multimodal generation architectures that jointly produce text and images have recently emerged as a promising direction for text-to-image (T2I) synthesis. However, many exi…
TV2TV: A Unified Framework for Interleaved Language and Video Generation
Xiaochuang Han, Youssef Emad, Melissa Hall +15
Video generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about…
Text-Guided Semantic Image Encoder
Raghuveer Thirukovalluru, Xiaochuang Han, Bhuwan Dhingra +2
Image encoders, a fundamental component of vision-language models (VLMs), are typically pretrained independently before being aligned with a language model. This standard paradigm…
Improving the Physics of Video Generation with VJEPA-2 Reward Signal
Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich +7
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…