This is the first work to formulate compression-aware abstention as a learning problem, in which a model learns to answer when supporting evidence survives compression and abstain when it does not, and controlled-deletion experiments show that the learned behavior is driven by evidence content rather than input length alone.
The framework, INFUSE, first stabilizes visual and textual representations around perturbation-averaged and ground-truth anchors, then aligns the stabilized representations across modalities with bidirectional contrastive objectives.
Aditi Sarker, Rafi Ibn Sultan, Hui Zhu et al.· 0 citations
Diversify, Anchor, and Filter (DAF), a stabilization framework that augments entropy-based adaptation with a marginal diversity loss that resists collapse, a cross-modal anchor consistency loss that constrains feature drift relative to a frozen source model, and feature salience filtering that skips low-value backward passes to offset part of the source-anchor overhead is proposed.
Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana et al.· 0 citations
Sensitivity-Guided Erasing Adaptation (SEGA) is introduced, a method for strict online continual TTA (CTTA) on corruption-style streams that yields consistent robustness and stability gains over strong CTTA baselines while reducing backward passes through sensitivity-based gating.
Chandler Timm C. Doloriel, Yunbei Zhang, M. Siddiqui et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Preliminary findings on a novel application of the tree depth prune instance hardness method to the TinyML system indicate that threshold control can change energy consumption with limited classification quality changes.
Tobiasz Puślecki, Krzysztof Walkowiak· 0 citations
Experiments show Influence-Directed Adaptive On-Policy Distillation (IDA-OPD), rather than relying on costly full-vocabulary Forward-KL objectives, preserves entropy-expanding updates while replacing entropy-contracting ones with divergence-adaptive advantage shrinkage, using only the teacher's sampled-token log-probability.
Run Yang, Runpeng Dai, Jie Sun et al.· 0 citations
This paper constructs quality-adjusted price indices for the AI inference market from public data and assembles 21,024 posted-price observations across 3,208 models and 86 providers and joins them to 4,605 benchmark scores through a latent quality index estimated from benchmark response patterns.
A unified probabilistic perspective on CP and DRO is developed by viewing both as ways to turn finite calibration data into a data-dependent quantile estimator that a test score falls below with high probability.
Kehan Long, Yiqi Zhao, Pol Mestres et al.· 0 citations
The Neural ODE-LMM is proposed, which embeds a Neural Ordinary Differential Equation (Neural ODE) within the linear mixed-effects framework: a learned vector field encodes covariate trajectories into a continuous-time latent state that drives both the fixed- and random-effect design, while preserving the standard LMM observation model.
Zhe Li, Q. Clairon, C. Samieri et al.· 0 citations
The study concludes that transformer models can, to some extent, learn patterns from MILP-optimized non-permutation flow shop schedules and that transformer-based scheduling represents an interesting direction for future research, particularly in settings with a fixed, recurring job set.
ButterMamba, a novel and efficient framework based on State Space Models (SSMs), achieves superior predictive accuracy with linear computational complexity by decoupling noise filtering from spatial-temporal modeling.
Limiao Zhang, Yuhe Lu, Jie Gao et al.· 0 citations
This work presents an evidence-gated multi-agent framework for transforming a natural-language MLOps cloud engineering task into a verified repository and operational cloud deployment and results show that the framework prevents unsupported lifecycle transitions and drives each run toward either a verified operational deployment or an auditable terminal failure.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
