Skip to main content
Search

Chinese University of Hong Kong, Shenzhen

5 related articles

Subscribe to updates
  1. arXiv

    Long-term memory becomes callable code: MaC lifts overall LLM-judge accuracy by up to 15.91% on LOCOMO while using fewer tokens

    Long-term memory systems usually store facts as entries and pick them by relevance at query time, which makes facts scattered across sessions and changing over time hard to compose. MaC puts memory construction and retrieval under one code abstraction: facts become executable functions with canonical identifiers and source references, and a query is compiled into a retrieval program that an executor runs after a single planning call. On LOCOMO and LONGMEMEVAL, MaC reaches the highest overall LLM-judge score in all four evaluation settings, improving over the strongest baseline in each by up to 15.91% and 9.06%, while substantially cutting token consumption.

  2. aclanthology.org

    TCM diagnosis stops being text-only: ShizhenGPT feeds tongue images, pulse, smell and sound into one 32B model

    TCM language models have been trained on under 1GB of text and handle text alone, while TCM diagnosis itself draws on looking, listening, smelling and pulse-taking. ShizhenGPT pairs more than 100GB of text from 3,256 TCM books and web sources with over 200GB of multimodal data, including 1.2M annotated images, 200+ hours of audio and pulse, smell and ECG signals, through two-stage pretraining and instruction tuning. On five 2024–2025 TCM exams ShizhenGPT-32B averages 78.1 against 84.0 for DeepSeek-R1-671B, and on a 7,204-question TCM vision benchmark it scores 63.6 against 61.4 for Gemini-3-Pro.

  3. Protein trajectories get an order, not just snapshots: two-scale autoregression cuts 400-frame drift from 8.62 to 1.78 Å

    Protein function depends on ordered transitions between conformational states, yet molecular dynamics sampling remains costly across large protein panels. TEMPO splits generation into two levels: a slow-scale model advances anchor conformations at the 20-ns training stride, and a fast-scale model generates 1-ns-spaced frames conditioned on those anchors. On held-out mdCATH and ATLAS proteins it reproduced MD ensemble observables; against a single-scale autoregressive model, 400-frame long-horizon RMSD error fell from 8.62 to 1.78 Å, and a 400-frame rollout took under 1 min.

  4. arXiv

    Meituan LongCat team lifts Qwen3 math reasoning by 1.67–2.75 points using teacher parameter-neighborhood perturbations

    The work introduces Neighborhood OPSD (N-OPSD): in on-policy self-distillation, local parameter perturbations of the reference-conditioned teacher yield a set of frozen experts; offline greedy selection builds a complementary pool by rewarding filtered reference-token gains beyond the pool's current best, and online routing uses MaxPeak to pick an anchor token and a quantile rule to pick the level of support among anchor-consistent experts, improving the three-benchmark Average@12 over OPSD by 2.75, 1.67, and 1.94 points on Qwen3-1.7B, 4B, and 8B, with only the distilled student needed at inference.

  5. arXiv

    TAPS adapts recurrent step size to the trajectory, lifting Sudoku accuracy to 91.39% and Maze to 79.90% while cutting the loops needed for matched quality

    The work introduces the Trajectory Adaptive Progress–Fluctuation Scheduler (TAPS), which uses exponential moving averages to estimate persistent progress and centered fluctuation in recurrent updates and adapts the per-step update scale online; it proves that under stated conditions TAPS reduces expected terminal loss and reaches a target quality in fewer loops, and empirically improves terminal accuracy with up to roughly 1.5x wall-clock speedup across Sudoku, Maze, language-model recurrence, and intermediate-layer recurrence.

You’re all caught up