Category
2,891 papers
This note argues that, at the level of trajectory generation and action-value updating, the distinction between Monte Carlo Tree Search and MC control is largely terminological.
Experiments show that PhyMamba achieves the best aggregated performance, with an overall mean error reduction of 31.8% compared with a diverse range of baselines, which supports practical deployment for robust battery health prognostics.
A novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time and significantly improves generalization under diverse distribution shifts and multiple model architectures is proposed.
A novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM) and outperforms conventional methods such as PointNet++ is proposed.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not directly represent the source modality, limiting the flexibility of some sampling algorithms; and (2) are unidirectional, preventing inversion (e.g., image-to-text). We propose BIT: Bidirectional Image-Text Diffusion Bridges. In contrast to previous approaches, BIT starts directly from text and interpolates into images, providing (1) a source-aware generative path that enables diverse and flexible sampling algorithms; and (2) an endpoint-conditioned process that can be traversed from image to text, providing a unified, bidirectional generative framework. BIT is derived through stochastic calculus, yielding SDE forms amenable to simulation and tractable loss functions that scale to high dimensions. Our experiments show that BIT is competitive with denoising-diffusion and deterministic-flow baselines, and outperforms them on several vision--language and natural-science evaluations.
The Hypergraph Adaptive waveLet Operator (HALO), which lifts the domain to a hypergraph and learns in its spectral wavelet domain, achieves best or near-best accuracy among frequency-, transformer-, DeepONet-, state-space-, and graph-based baselines and sustains stable multi-step rollouts.
This work introduces FeatureFormer, a neural performance predictor that incorporates explicit node-wise encodings of FLOPs, parameter counts, and memory proxies within a gated graph attention architecture and presents NNEQ, a new large-scale energy consumption dataset that enables unified evaluation of latency and energy prediction.
This paper studies the role of model initialization in federated STLF, and proposes two initialization strategies from global and local perspectives, which effectively improve forecasting performance, as evidenced by reduced client drift, improved convergence behavior, and lower forecasting errors.
This framework separates temporal alignment, plasticity, forgetting, and bounded rehearsal in recurrent sequence models, together with numerically stable positive-decay renormalization, to remain competitive in language modeling and improve length extrapolation on variable-digit addition.
Overall, it is found that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks.
A supervised energy-distance distillation method is introduced that compresses a multi-step diffusion teacher into a single-step student by aligning student forecasts with teacher samples and ground-truth observations and preserves skill for extreme events.
It is demonstrated that deep latent representations extract clinically relevant signatures from noisy signals, enabling precise, rapid, and data-efficient diagnosis.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
General Science
Climate & Sustainability
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
A new algorithm learns to anticipate the unprecedented scenarios that critical infrastructure and global supply chains are least prepared for.
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
