Tracked topic
…Memory-Efficient Parallel Token Generation via Dual-View Diffusion Published on May 12 Submitted by Nguyen Van Chien on May 14 Authors: Chien Van Nguyen , , , , Franck Dernoncourt , Abstract Orthrus is a dual…
…A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages Published on May 13 Submitted by Suparnojit Sarkar on May 14 Authors: , Suparnojit Sarkar , Piyush Patel Abstract A parallel…
…Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs Published on May 12 Submitted by Jonas Geiping on May 13 ELLIS Institute Tübingen Authors: , , , Jonas Geiping Abstract Language models can…
…Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents Published on May 8 Submitted by Xichen Zhang on May 11 Xiaohongshu Authors: Guankai Li , , Yi Xu , Xichen Zhang , Abstract HyperEyes…
…To address this, we develop a chunkwise parallel algorithm for LA with a stepwise momentum rule by geometrically reordering the update coefficients. Further, from a dynamical systems perspective, we analyze the momentum…
…The following papers were recommended by the Semantic Scholar API Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models (2026) PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding…
…In parallel, reward models have become increasingly important for RL-based image editing optimization, yet existing reward model benchmarks still rely on unrealistic evaluation settings that deviate from practical RL scenarios. These…
…Parallel Representative Tokens for Retrieval with Diffusion Language Models Published on May 8 Submitted by shuai wang on May 11 The Information Engineering Lab Authors: , , Shengyao Zhuang , , Abstract DiffRetriever enables efficient multi…
…AI-generated summary We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete trajectory tokens and generates them through parallel masked…
…We identify this skill as a two-stage pipeline, i.e., parallel reasoning then summarization , which can operate beneath any agentic harness . We present a systematic empirical study of HeavySkill across diverse…