Skip to main content
Search

Jilin University

8 related articles

Subscribe to updates
  1. bioRxiv

    TriStageHLA splits epitope discovery into three stages, lifting immunogenicity AUROC from 60.1% to 81.4%

    A team including City University of Hong Kong released TriStageHLA, which splits HLA class I epitope discovery into peptide-only screening, allele-specific binding prediction and immunogenicity prediction in sequence. On held-out immunogenicity data the immunogenicity module reached AUROC 81.4% and AUPRC 73.8%, above ImmuneApp at 70.7%/63.6% and BigMHC-IM at 60.1%/51.5%; the binding module reached AUROC 96.2% and AUPRC 95.2% on combined BA/EL evaluation. In a simulated screen over 300,000 human-proteome background peptides, the screening stage kept 82.4% of true candidate peptides while discarding 87% of background peptides.

  2. arXiv

    Dynamic-graph prediction without per-graph retraining: interaction histories become tables a frozen tabular model can rank

    CL-DGFM encodes interaction histories on dynamic graphs as tabular features independent of node identity, covering repeated contacts, indirect connectivity and ordered destination transitions, then lets a pretrained tabular foundation predictor learn from diverse synthetic dynamics how to read them. It achieves the highest mean MRR on 10 of 13 datasets across TGB and TGB-Seq, exceeding the strongest listed baselines by 10.78, 15.24 and 11.69 percentage points on Comment, Flickr and YouTube, and transfers to real graphs without target-graph parameter updates.

  3. arXiv

    Diffusion language models stop reusing one steering vector: feeding the previous prediction back lifts TruthfulQA multiple-choice average from 30.89 to 45.42

    TraceSteer feeds a diffusion language model's previous denoising prediction back into activation steering, adapting both the correction direction and its strength step by step, and improves factual reliability on TruthfulQA for LLaDA-8B-Instruct and Dream-7B-Instruct.

  4. arXiv

    Beyond whether an image is AI: EviScene checks the depicted situation, reaching 52.26% evidence sufficiency

    Image factuality assessment no longer stops at whether a picture is AI-generated: the EviScene multimodal agent refines its own questions during investigation and reaches 79.05% balanced accuracy and 52.26% evidence sufficiency on 1,527 test images.

  5. arXiv

    Plane-wave DFT Hamiltonians become learnable: projectability-selected eigenstates cut sodium band errors to 1–3 meV

    Converting plane-wave DFT Hamiltonians into atomic-orbital form now uses projectability-selected eigenstates to complete the subspace instead of an empirical shift, giving 1–3 meV band errors for five sodium phases with 13 orbitals per atom where real-space reconstruction needs 23 orbitals and still errs by 12–28 meV.

  6. arXiv

    MoonGS reconstructs lunar terrain from image pairs with a frozen vision foundation model and semantic ranking loss, reaching 23.80 dB PSNR on LuSNAR

    MoonGS is a feed-forward 3D Gaussian Splatting framework for lunar scenes: given only two images it predicts pixel-aligned Gaussian primitives in a single forward pass with no per-scene optimization, using robust depth features from a frozen vision foundation model (DUSt3R, or VGGT), semantic priors plus a semantic ranking loss to regularize weakly textured background depth, and an entropy-guided heuristic resampling strategy to augment sparse observations. On the LuSNAR benchmark and the authors' weak-texture MoonBlender dataset it outperforms feed-forward NeRF/3DGS baselines on PSNR, SSIM and LPIPS while keeping sub-second inference.

  7. arXiv

    JEV-like direct-decision models use only 67–76% of the effective ordinal label space across 36 datasets, and BA-LoRA post-training lifts utilization from about 47% to 86%

    Analyzing JEV 1.13 and three open KEV models (0.8B/4B/9B), the study finds that on ANLI JEV reaches 74.95% accuracy yet assigns 38.8% of predictions and 51.3% of errors to Neutral, and across 36 ordinal datasets final decisions cover only 67–76% of the effective gold support (versus 87–102% on four nominal tasks); through candidate-order randomization, same-item scale refinement from K=2 to K=14 (utilization falling to 26–75% at K=14), and targeted BA-LoRA post-training (gold-relative utilization rising from roughly 47% to 86% on eight supervised scales), it shows this ordinal scale-utilization bias is a learned and modifiable decision-stage compression of the candidate space.

  8. Retina

    Oracle-curated synthetic fundus images lift ConvNeXt diabetic retinopathy grading kappa from 0.6350 to 0.7695 and double proliferative DR recall

    The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.

You’re all caught up