Category
3,595 papers
STGAT (Spatio-Temporal Graph Attention Network), a clock-dynamics-aware anomaly detection solution that jointly models temporal distortion and inter-device consistency in energy IoT systems, is introduced.
It is suggested that diffusion post-training selectively preserves or reorganizes inherited computation according to task structure, rather than uniformly replacing autoregressive mechanisms.
X-FED is proposed, a novel Conflict-Aware Cross-Client Federated Exit Distillation framework that jointly addresses both client- and depth-wise conflicts while extending PFL to early-exit networks and introduces a client-decoupled formulation that reduces communication overhead with theoretical soundness.
BAFA, the Bounded Active Fairness Auditor is introduced, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs, suggesting that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper formalizes KV management as a causal system of three primitives: KV Admission, Selection, and Eviction, and instantiate KV Admission via Write-Gated KV (WG-KV), a lightweight mechanism that learns to predict token utility before cache entry.
Kascade is a training-free sparse attention method that leverages known observations such as 1) post-softmax attention is intrinsically sparse, and 2) the identity of high-weight keys is stable across nearby layers to achieve high accuracy on long-context LLM inference.
It is found that explicit world-modeling yields better representations in terms of higher probing accuracy and steerability of the model, and that better representations yield larger gains from GRPO, especially on harder cube states.
ScalePRM, which scales verification compute as an alternative to ground-truth supervision for training process reward models, generates multiple independent verifications of each reasoning step and aggregate their judgments to produce synthetic step-level labels without ground truth.
To further accelerate speculative decoding in long-context generation, SpecPV is introduced, a self-speculative decoding approach that performs fast verification using partial key-value states (KV) and periodically applies full verification to eliminate accumulated errors.
This work shows that the multiplicity within a large Rashomon set enables reactive robustness and increases information leakage, and highlights the dual role of Rashomon sets as both a resource and a risk for trustworthy ML.
A curiosity-driven quantized Mixture-of-Experts framework that addresses both accuracy and stability through Bayesian epistemic uncertainty-based routing across heterogeneous experts, suitable for safety-sensitive edge deployments where both accuracy and predictability are critical.
By reframing DODE as a sequential decision-making problem, this approach addresses the credit assignment challenge through a learned policy and provides a novel framework for calibration of microscopic traffic simulations.
Machine Intelligence
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
