Skip to main content
Search

Sun Yat-sen University

14 related articles

Subscribe to updates
  1. medRxiv

    Colorectal cancer recurrence after surgery gets a spatial host-microbiome readout: AUC 0.81 versus 0.45 for standard pathology

    Whether colorectal cancer recurs after resection has been judged mainly from routine pathology such as lymphovascular invasion, perineural invasion, tumor budding and Ki-67. AlphaFISH pairs a sequencing-free nanoprobe biochip with a transformer model to read 41 host transcripts and 51 bacterial genera across 149 colorectal biopsies, and in 28 patients followed for one year after surgery it predicted recurrence or metastasis with an AUC of 0.81, against 0.45 for the combined routine clinical markers. The result comes from a preprint that has not been peer reviewed, on a limited sample.

  2. CircRNA binding-site prediction stops reading only the RNA: CPRISP encodes the protein too, reaching mean AUC 0.9874 across 37 benchmarks

    Prediction of circRNA-RBP binding sites has leaned on transcript features while making limited use of protein-specific information. CPRISP feeds circRNA sequence composition, physicochemical properties, secondary structure and pretrained embeddings together with global and local protein-sequence representations into a multi-scale residual classifier. Across 37 benchmark datasets it reaches a mean AUC of 0.9874 versus 0.9230 for CircSSNN, and holds 0.9861 under sequence-similarity-controlled partitions.

  3. arXiv

    Diffusion caching stops trusting raw probe drift: dividing by trajectory movement cuts LPIPS at the same compute

    A training-free diffusion caching rule spends its exact denoiser evaluations where they matter by dividing shallow-probe output change by input displacement, lowering median LPIPS at matched exact-compute budgets on FLUX.1-dev, Wan2.1 and Open-Sora 1.2.

  4. arXiv

    Visual reasoning drops coordinate regression: a probe token samples evidence over visual tokens, hitting 78.0% on 4K with about 1.2% of the tokens

    TiCO replaces coordinate regression in thinking-with-images with a probe token that samples evidence over visual tokens, reaching 78.0% overall accuracy on HR-Bench 4K while generating only 6.2 tokens per query.

  5. Genome Medicine

    Methylation sequencing also carries fragmentomics: plasma cfDNA blocks give cancer tests an interpretable second signal

    Plasma cell-free DNA methylation sequencing, long used only to read methylation, is shown to partially retain fragmentomic signals such as fragment length and end motifs. The study delineates co-methylated blocks directly in plasma cfDNA, places methylation and fragmentomic features in the same genomic intervals, and builds an interpretable ensemble model for cancer detection and tissue-of-origin prediction. Cross-platform comparisons show major fragmentomic patterns are recapitulated in methylation sequencing, though preservation varies by feature.

  6. arXiv

    Storage prefetching stops guessing from file offsets: user-space policies cut app cold start by 5.3–26.3%

    Linux readahead infers the next page from recent file offsets, which fails when accesses follow workload structure such as sparse startup reads, B-tree key-order traversal, or tensor-layout model loading. PredictIO separates prediction from execution: the kernel delivers observed accesses and application hints to user-space policies, which emit uniform page-range requests that a kernel backend validates, bounds, and issues as asynchronous prefetch I/O. Across application launch, SQLite range scans, and llama.cpp model loading, latency drops by 5.3–26.3%, scans speed up by up to 2.99, and model loading drops by 8.8–47.9%.

  7. arXiv

    Picking one speaker out of overlapping speech: a 5.2M frontend spends compute by difficulty, cutting WER from 16.8% to 14.6%

    Target speaker extraction for multilingual overlapping speech no longer applies one fixed computation depth to every input. Fixed-depth frontends either under-process hard inputs or waste computation on inputs that have already converged. LATTE uses a difficulty estimator to route each mixture through two, four, or six shared extractor blocks, reaching 15.07 dB macro SI-SNRi at 0.30 GFLOPs on the eight-language PolyExtract benchmark, within 0.09 dB of a 0.53-GFLOP fixed-depth path while cutting computation by 43.4%; before frozen Qwen3-Omni it lowers average WER from TF-GridNet's 16.8% to 14.6%.

  8. arXiv

    OnlineQAT uses on-policy distillation on student-generated prefixes to lift Qwen3-1.7B to a 57.28 six-task average at W3A16, 2.90 points above ReasoningQAT

    OnlineQAT is a two-stage ultra-low-bit recovery framework that first obtains a usable W2/W3 initialization through block-wise quantization-aware training, then performs on-policy distillation on responses sampled from the quantized student, with a frozen full-precision teacher supplying a sampled reverse-KL signal at each visited prefix; on Qwen3-1.7B it reaches six-task averages of 57.28 at W3A16 and 32.52 at W2A16, improving over ReasoningQAT by 2.90 and 0.44 points, suggesting that student-visited states offer a recovery signal beyond fixed-completion training, particularly at three bits.

  9. arXiv

    HarnessSecurity-Bench tests six coding agents: enabling auto-approve raises attack success from 29.2% to 95.6%

    The work builds a ten-mechanism taxonomy across 40 coding agent harnesses and rates 400 harness–mechanism cells (205 confirmed implemented, 83 confirmed absent, 112 unresolved), then introduces HarnessSecurity-Bench, which runs 2,500 trials under GLM-5.2 on 23 tasks across five attack surfaces with separate deterministic oracles for six harnesses, finding that enabling auto-approve raises attack success from 29.2% to 95.6%, that network isolation and read-only mode cut attack success from 57.1% and 8.3% to 0.8% at utility losses of 24.5 and 34.0 percentage points, and that command allowlisting and denylisting reduce attack effects with a small utility loss and a utility gain respectively.

  10. arXiv

    GraphBind binds multimodal semantics through graph topology, reaching up to 28.1% relative gains over 11 baselines

    The work proposes GraphBind, a topology-driven approach that binds rich modality information into a unified shared space for multimodal graph foundation models, using topology to organize self semantics and reliable neighborhood semantics and adapting that space to discriminative and generative tasks through lightweight interfaces; experiments against 11 representative baselines report leading performance on both task types, with relative improvements of up to 28.1% over the strongest baseline.