Skip to main content
Search

University of Massachusetts Amherst

6 related articles

Subscribe to updates
  1. arXiv

    Production AI optimization stops reading only failures: CoCoEvolve hits 92.8% hard accuracy on DABStep

    Evolutionary optimization for production AI systems no longer picks one candidate from the search frontier and rewrites it from its failures alone. CoCoEvolve has an agentic mutator retrieve evidence from the entire evolutionary history and probe the live system before proposing changes. On DABStep it reaches 92.8% held-out hard accuracy, against 78.4% for Meta-Harness and 30.4% for GEPA under matched conditions; on data-eng-bench it lifts test-set solve rate from 59.1% to 77.4%, past the 73.6% best baseline.

  2. arXiv

    SoftServe builds positive-definite curvature estimates from a variational objective and reaches lower losses than Adam, Muon, and SOAP on ill-conditioned deep learning tasks

    The authors introduce SoftServe, a family of quasi-Newton methods that derives positive-definite curvature estimates from the variational objective of Berglund et al. (2025), remaining positive definite even under negative curvature, and offers diagonal and Kronecker-factored variants that preserve positive definiteness by construction; it relies on the stable coupled Newton-Schulz iteration to replace costly matrix decompositions with GPU-friendly matrix multiplications, and on severely ill-conditioned problems such as recurrent networks, deep autoencoders, physics-informed neural networks, and a 136M-parameter physics-informed diffusion model it often achieves lower losses than established baselines including Adam, Muon, and SOAP.

  3. arXiv

    TellTail identifies the deployed embedding model among 53 retrievers from queries alone in black-box systems

    The work introduces TellTail, a query-only fingerprinting attack that identifies the embedding model behind a black-box retrieval system: it perfectly identifies the deployed retriever from full rankings, achieves 94.3% success from unordered top-3 results, and 92.5% from language-model-generated answers alone, and still identifies 44 of 53 retrievers in an end-to-end OpenWebUI deployment.

  4. arXiv

    A survey unifies joint, cross-modal and joint-editing video-audio generation on one distribution and gives the first systematic taxonomy of joint audio-visual editing: nine categories, 28 edit types

    Observing that video and audio are perceived together yet most generative models treat them in isolation, this survey casts joint generation, cross-modal generation (one modality from the other) and joint editing as three problems defined on a single distribution over audio-visual pairs, organizes the field around one question—how the output is kept coherent across modalities in time and semantics—proposes a taxonomy along five design axes (generation strategy, audio representation, video representation, alignment enforcement, pretraining reuse), and, to the authors' knowledge, provides the first systematic taxonomy of joint audio-visual editing, mapped as nine edit categories spanning 28 edit types, together with methods, datasets and metrics for each setting and a closing list of open pr

  5. 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).

  6. When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-like Caregiver Support

    In the context of family caregivers of people living with Alzheimer's Disease and Related Dementias (ADRD), this work compares caregiver support exchanges from online communities with peer-like responses prompted from three LLMs (LLaMA, GPT-4o-mini, and MedGemma), using psycholinguistic and qualitative analysis to show that peer responses used significantly more first-person and past-focused language than peer-like AI responses, identifies seven types of personal narratives in human peer support, and finds that AI often captures their emotional work while potentially fabricating experiential grounding, thereby naming a narrative authenticity gap and a synthetic lived experience paradox.

You’re all caught up