Trending
We present FunnelAL, a retrieve-then-rank active learning system for single-class discovery, which adapts the multi-stage funnel architecture of industrial recommender systems to data annotation. Large-scale supervised learning faces two…
Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations. Although recent diffusion-based methods have substantially improved perceptual quality, their current designs leave two…
In the proper variant of the classical hat-guessing game on a graph, an adversary properly colors the vertices from a palette of $q$ colors. Each vertex sees only the colors of its neighbors and simultaneously guesses its own color; the…
Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused Adaptive Prediction Sets (DAPS) is a widely used graph-aware diffusion baseline,…
We propose a randomized iterative method for the ordinary least-squares estimation problem in large-scale linear statistical models, namely the Sequential Preconditioned Conjugate Gradient Method (SPCG). SPCG constructs a sequence of…
Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data…
Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail. We study this source choice as…
Motivated by recent advances in derivative Bohr inequalities and their refinements, we investigate the Bohr phenomenon for holomorphic mappings in complex Banach spaces associated with Schwarz functions. We establish sharp Bohr-type…
Ranking is a fundamental component of modern information access systems. Reinforcement learning (RL) provides a flexible framework for directly optimizing coarse-grained feedback and system-level objectives defined over the complete ranking…
We investigate a spin-degenerate Fermi gas coupled to a high-finesse optical cavity, where the competition between scalar and vectorial couplings is controlled by the relative polarization angle of the pump and cavity fields. We find that…
Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of relevant content decreases sharply as video sequence length increases, and exposing the…
Many variational descriptions of quantum many-body systems rest on an expansion over basis functions, and their practical limit is often set by the number of basis functions required. We propose the Bayesian variational method (BVM), in…
High-power laser systems increasingly rely on multi-beam processing to enhance manufacturing throughput. However, conventional multifocal systems remain constrained by bulky architectures, stringent alignment requirements, and…
Low-temperature magnetoresistance loops of compacted CrO2 powders become strongly nonmonotonic when electrical transport is dominated by a small number of spin-dependent intergranular tunnelling paths. We reanalyse previously reported data…
Type safety has traditionally rested on carefully crafted type systems, under the motto "well-typed programs cannot go wrong". Modern demands push type systems past this basic guarantee: toward memory safety (e.g., Rust), stronger…
The cold dark matter paradigm successfully explains large-scale structure but faces persistent tensions on small scales. Warm dark matter (WDM) with $\mathrm{keV}$-scale particles can alleviate these issues by suppressing small-scale…
Fuel-dominant powered descent can be written as a convex program, but the usual full-state epigraph formulation still carries many state variables, fuel epigraph variables, and dynamics equalities. In addition, the pure-fuel objective…
We present the analysis of two planetary microlensing events, KMT-2025-BLG-0975 and KMT-2025-BLG-1160, discovered during the 2025 Galactic bulge microlensing season through high-cadence survey observations. In both events, short-duration…
Hedging a derivative position under transaction costs and market frictions requires a trading rule that adapts to changing conditions. Deep hedging trains a neural policy for this task but policy training does not determine whether a…
Item Response Theory (IRT) has recently been proposed as a framework for evaluating large language model (LLM) benchmarks by separating a model's latent ability from the properties of individual benchmark items. Existing neural IRT…