The paper introduces ImpossibleRubrics, a benchmark with 169 impossible tasks and 48 answerable controls to test the robustness of language model-generated rubrics as reward signals. It shows that some rubrics can be exploited by adversarial answers, revealing a rubric-quality gap rather than task impossibility.
The chart will appear after repeat observations. The current metric comes from the source.
2 source votesReal observations only. History before source connection is not reconstructed.
This research helps evaluate the reliability of AI-generated rubrics in preventing adversarial manipulation, important for fair automated grading and reinforcement learning systems.
StepAudio 3 Realtime is an audio-language foundation model designed for real-time spoken interaction, featuring a continuous listen-converse-think-act loop. It includes Deep Perception for interpreting user intent, Seamless Duplex for handling audio stream synchronization, and Think-While-Speaking to balance reasoning and latency. The model achieves high performance on benchmarks like MMSU and Artificial Analysis Full-Duplex, along with a task-success rate on τ-Voice.
4 days agoDaily PapersThe paper discusses recursive self-improvement (RSI) in AI systems, outlining its development roadmap from autonomy in improvement execution to recursive meta-improvement. It examines RSI across various scenarios like scientific discovery and software engineering, highlighting different requirements and development speeds.
6 days agoDaily PapersStepAudio 3 Music is a large-scale music generation model that uses explicit musical planning and text control. It employs a flow-matching diffusion Transformer to predict audio latents, with a discrete-continuous design and a Mixture-of-Experts autoregressive model for structured music generation.
5 days agoDaily PapersThe paper introduces Vidu S2, a system with two components: Vidu S2-Avatar for real-time interactive digital characters and Vidu S2-Editing for real-time video editing. It also explores real-time spatial video generation for both components. Compared to its predecessor, Vidu S2-Avatar offers improved real-time 720p video generation, dynamic reference updates, and enhanced instruction following. Vidu S2-Editing enables real-time video stream editing with features like style rendering and background replacement.
6 days agoDaily PapersPhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.
2 days agoDaily PapersLynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.
2 days ago