Qwen-Planner-Agent explores using AI systems as active participants in building next-generation AI, via a closed-loop ‘AI-for-AI’ framework applied to mobile…
Eliminates the resource-heavy teacher+critic distillation stack (Distribution Matching Distillation) used for few-step causal video diffusion, replacing it with generator-only post-training…
Reworks world-action models for robot control so they predict sparse visual deltas plus actions instead of dense future frames, decoupling…
Proposes an RL post-training framework for joint audio-video diffusion generation that fixes credit-assignment problems from entangled multimodal rewards and the…
Researchers propose ‘disaggregated quantization,’ which applies distinct quantization schemes to the prefill and decode phases of LLM inference instead of…
The paper introduces PISA, a hierarchical block-sparse attention mechanism that replaces exhaustive query-block scoring with coarse-to-fine selection over a hierarchy…
The paper identifies a credit-assignment flaw in RL training for tool-calling LLM agents: because agent outputs mix structured tool calls…
Researchers introduce Self-Organizing Agent Teams (SAT), fixed groups of AI agents that learn reusable collaboration strategies from as few as…
RewardVerse introduces a rubric-based reward framework for RL-trained video generation models, addressing scalar drift in reward models that map subjective…
HyperQ adds token-conditioned quantum residual branches to a frozen masked-diffusion language model, where a lightweight circuit hypernetwork emits per-token rotation…
Uranus is a data-driven robot simulator built on a joint-trajectory-conditioned autoregressive diffusion model that generates streaming, open-ended video rollouts from…
GAE, a geometry-native autoencoder, reparameterizes features from a geometry foundation model into a compact latent space jointly decodable to appearance,…
