Tracked topic
…Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models (2026) AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression (2026) Spectral Evolution-Guided…
…A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning Published on Jun 9 Submitted by Heming Zou on Jun 11 Tencent Authors: Heming Zou , , , , , , , , , , , Abstract TRACE is a rollout allocation…
…Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling Published on Aug 3 Submitted by JiajunLiang on Aug 5 Nanjing University Authors: Jiajun Liang , , , Jiazhe Wei , , , , , , , , , , , Chenyang Si Abstract AURORA-LM is…
…Then, we adopt reward-conditioned quality control and Engram conditioning , along with Unified MoE for multi-task and multi-audio-modality modeling. In addition, we use curriculum learning and GRPO post-training…
…EgoForce operates across fisheye, perspective, and distorted wide-FOV camera model s using a single unified network. Our approach combines a differentiable forearm representation that stabilizes hand pose, a unified arm-hand…
…An AutoRegressive Large Multimodal Model with Unified Discrete Representations (2026) Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification (2026) InsightTok: Improving Text and Face Fidelity in Discrete…
…Zhifei Xie , Zihang Liu , , , , , , , , , Abstract A unified streaming audio model is developed that combines offline task execution with real-time audio instruction following through an end-to-end framework supporting multiple audio…
Papers arxiv:2605.04569 Lightning Unified Video Editing via In-Context Sparse Attention Published on May 6 Submitted by taesiri on May 7 Authors: , , , , , , Abstract In-context sparse attention framework enables efficient…
…A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents Published on Jun 30 Submitted by qianchu liu on Jul 2 Microsoft Authors: , , , , , , , , , , , , , , , , , , Abstract HealthAgentBench presents a comprehensive…
…Training and Benchmarking Scene Text Editing (2026) Qwen-Image-2.0 Technical Report (2026) FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching (2026) HiDream-O1-Image: A Natively Unified…