Skip to main content
Search

Monash University

18 related articles

Subscribe to updates
  1. arXiv

    Multimodal reasoning models can forget one face without forgetting the person: VKCR confines unlearning to the image channel

    Multimodal large reasoning models can pull sensitive information back through cross-modal associations inside intermediate reasoning, so suppressing the final answer is not enough. VKCR reframes the forget target as one designated image-to-knowledge association: it localizes the edit in a compact association-conditioned low-rank parameter subspace, then counterfactually rebinds the affected reasoning branch, weakening target-bearing or unsupported continuations while favoring evidence-grounded non-sensitive alternatives. On CLEAR-R and MLLMU-R it reduces both image-conditioned target leakage and hallucinated reassociation while preserving non-sensitive visual reasoning and permitted text-only access to the same knowledge.

  2. arXiv

    Streaming video-to-audio closes the alignment gap: LiveFoley needs only 0.08 s of frontend look-ahead and runs at 156 ms end-to-end

    Real-time video-to-audio has been held back by two bottlenecks: visual frontends shrink their receptive fields to cut look-ahead, and causal diffusion backends denoise each patch in isolation, so both alignment and audio quality trail offline models. LiveFoley uses a trailing sliding window to turn off-the-shelf non-causal segment-level encoders into streaming modules without retraining, cutting frontend look-ahead to 0.08 s, and widens the backend denoising window toward history. On the VGGSound test set, LiveFoley-48k reaches a DeSync of 0.48, on par with offline MMAudio-L at 0.47, with 156 ms end-to-end latency on a single A800 GPU.

  3. arXiv

    An agent writes its execution experience into reviewable skills: DrugHarness designs and synthesizes an HPK1 compound with 14.19 nM cellular IC50

    Computational drug-discovery agents usually rebuild their tool calls for every task, so a successful strategy rarely carries over. DrugHarness places more than 80 scientific operations and biomedical resources in one workspace, induces action hypotheses with explicit applicability conditions from execution trajectories, and admits them as skills only after an independent review agent checks sources and runs targeted trials when needed. On MolBench, the configuration without evolution reaches 91.9% affinity-comparison accuracy, 10.8 percentage points above reported MolClaw-CC results; in retrospective evaluation, frozen learned skills raise Qwen's optimization success from 79.5% to 87.2%.

  4. arXiv

    History Forcing teaches few-step video models to remember: a 1.3B student reaches 79.82 on 60-second VBench-Long

    Few-step autoregressive video diffusion models gradually lose subject and scene information over long rollouts, and existing distillation targets do not constrain distant history separately. History Forcing builds a context residual from the difference between one autoregressive teacher's predictions with and without extra history, then weights it into the DMD or OPSD distillation target. A 1.3B student reaches a VBench quality score of 85.07 for 15-second generation and a VBench-Long aggregate of 79.82 for 60-second generation, and raises PlayWorld Evolution Quality from 2.35 to 2.70 when the camera leaves and returns.

  5. arXiv

    Interactive video world models treat old frames as false: re-dating by valid time lifts the current-state share from 0.36 to 0.62 after an undo

    Interactive video world models draw frames from a memory bank stamped with capture times, and a frozen generator reads the newest timestamp as truth, so after an agent undoes an action the only view of the present is an older frame judged outdated. ReDate keeps every frame and re-dates retrieved tokens by valid time read from the action log, so a reverted region reads as one that has just reached a new state, with no training. On FAR's 352 reverted steps the current-state share rises from 0.36 to 0.62 and the outdated share falls from 0.27 to 0.09; on HY-WorldPlay it rises from 0.003 to 0.19.

  6. Close one lane and the real-time demand calibration gets sharper: 63% lower density error than LimEKF on grid day 10

    A real-time OD demand calibration framework couples a data-driven demand-prediction network with a black-box microscopic traffic simulator in both directions, using an analytically tractable metamodel to carry gradients back so network parameters and demand estimates update together at each time step. In a 3×3 grid network, after link B1C1 closed at hour 4 on day 10, density MSE was 21.6 [veh/km]2 versus 57.9 [veh/km]2 for LimEKF, a 63% reduction; on the Tokyo expressway corridor during the 2021 Games travel-demand-management day, the online-updated version reached 0.66 [veh/km]2 against 1.15 [veh/km]2 for LimEKF.

  7. EEG attention decoding drops the fixed electrode graph: dynamic topology plus self-attention reaches 91.67% on three classes

    EEG attention recognition has moved away from a fixed electrode-connectivity graph. Multi-band features were previously concatenated and channel relations were handled with a preset adjacency matrix, which struggles to capture task-dependent coupling. DGCSA treats electrodes as graph nodes, updates channel topology through a learnable adjacency matrix, and adds self-attention for global dependencies, while Bayesian-optimized band weights fuse power spectral density and differential entropy. On 873 three-second EEG segments from 20 participants, three-class accuracy reached 91.67%, above SVM, CNN and LSTM baselines; mean attention scores were also higher in VR than in 2D.

  8. Limestone thin sections get a lighter backbone: 2.095M parameters, 91.11% accuracy across six classes

    Limestone thin-section classification now runs on a compressed MobileNetV3 backbone that folds texture enhancement and multi-level feature fusion into one lightweight network. Fine-grained carbonate grain boundaries and micritic matrix were previously attenuated by successive downsampling, while inter-class similarity stayed high and manual petrographic reading depended on expert judgment. On 3,600 images of six classes collected in Ordos, Xinjiang, Tibet and the Lesser Khingan Mountains, the method reaches 91.11% accuracy with macro precision, recall and F1 of 91.28%, 91.11% and 91.12%, at 2.095M parameters.

  9. After reviewing 922 citations, 41 international experts extended the acute exacerbation definition from IPF to all fibrotic interstitial lung diseases and proposed a new acute respiratory worsening framework

    An international multidisciplinary working group of 41 experts systematically reviewed 922 citations up to March 17, 2025, revised the 2016 acute exacerbation (AE) definition—previously limited to idiopathic pulmonary fibrosis (IPF)—into an AE-fILD definition applicable across all fibrotic interstitial lung diseases (anchored in diffuse alveolar damage with or without organizing pneumonia), proposed the broader concept of acute respiratory worsening (ARW) to capture acute deteriorations not attributable to DAD, and summarized evidence on epidemiology, risk factors, prognosis, and management while discussing AE as a clinical trial endpoint.

  10. A radiomics model automatically separated thermograms of 98 CRPS patients from 56 healthy controls with AUC 0.93, outperforming three clinicians

    Using 178 thermograms from 98 patients with complex regional pain syndrome (CRPS) and 837 thermograms from 56 healthy controls, the study used a U-Net deep learning model to segment extremities automatically (mean Dice similarity coefficient 0.99), extracted 564 radiomics features per extremity per thermogram (intensity, shape, texture), and built a classification model with the WORC automated machine learning framework under 20x random-split cross-validation; the model distinguished CRPS from healthy control thermograms with a mean AUC of 0.93 (95% CI 0.90-0.97), statistically significantly better than three clinicians' 0.82, 0.79, and 0.69 (P < 0.001).