Latest papers
Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architectures (JEPAs) avoid explicit negative-pair construction and raw-input reconstruction by…
Can image-editing models discover visual rules in image space and complete problem-solving end-to-end? We tackle this question in the spirit of a human worksheet test (e.g., an IQ test), using problems that require models to read…
Single-photon avalanche diode (SPAD) cameras are promising for low-light and high-dynamic-range intensity imaging, but their practical use is limited by complex sensor-specific noise. Unlike time-correlated single-photon counting (TCSPC)…
Light incident on an insulator is generally not expected to turn it into a metal without invoking intense ultrafast excitation that leads to transient structural transitions. Here we show that magic-angle twisted bilayer graphene tuned to…
In recent years, Low Earth Orbit (LEO) satellites have been increasingly deployed to enable connectivity in remote and disaster-prone areas. Researchers have proposed Orbital Edge Computing, which adds computational intelligence to LEO…
Accurate prediction of object trajectories during manipulation is essential for closing the perception-action loop. Progress is limited on two fronts: available datasets lack fine-grained language-to-motion annotations, and existing…
Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness only as a trajectory-level reward, which provides limited…
Soft robotic substrates are promising for Physical Reservoir Computing (PRC) because their compliant nonlinear dynamics can provide temporal memory, high-dimensional state transformations, and efficient inference. However, physical…
Neural Video Codecs (NVCs) offer unprecedented rate-distortion performance, making them highly attractive for bandwidth-constrained environments like 5G cellular networks and emerging satellite direct-to-cell (D2C) links. However, deploying…
We prove sequential convergence results for the AdaGrad algorithm family optimizing convex differentiable objectives. Specifically, we provide necessary and sufficient conditions for the convergence of iterates for the three main AdaGrad…
One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models (LLMs), yet existing approaches trade either quality (WANDA) or compute cost (SPARSEGPT). We introduce F-WANDA, a drop-in modification of…
Erroneous vibration signals caused by sensor malfunction, shutdown transients, and abnormal acquisition conditions can degrade the reliability of automated industrial monitoring pipelines. This paper presents a deployment-oriented analysis…
It is well known that the number of partitions of $[n]$ without singletons equals the number of partitions of $[n]$ in which no block contains two cyclically adjacent elements $i,i+1\pmod{n}$. Bernhart remarked that there might be no simple…
Emotional Support (ES) systems have long optimized a single objective: alleviating the user's emotional distress in the moment. We argue that a complementary need, helping users see themselves more clearly, defines a distinct paradigm we…
We identify a physical-space balance-law mechanism underlying bilinear null forms for the free Dirac equation in three space dimensions. For each spatial direction, we decompose a spinor into the two eigenspaces of the directional Dirac…
All-sky surveys in the soft X-ray band are essential for detecting transient objects such as high-redshift gamma-ray bursts (GRBs), which provide key insights into the early universe. HiZ-GUNDAM is a future satellite mission designed to…
We investigate a coupled thermoelastic plate system consisting of a fourth-order displacement equation and a heat evolution equation linked through a spatially varying coupling factor $\alpha(x)$. The model accounts for thermoelastic…
Streaming data-driven dynamic multi-objective optimization requires algorithms to track time-varying Pareto fronts using only sequential observations under concept drift. However, systematic evaluation remains difficult because real-world…
Architectural drawings violate the usual assumption behind multi-view reasoning: plans and sections are cuts, while elevations are facade projections, so corresponding components change appearance in ways camera motion cannot explain. We…
Ultralight axions from string compactifications carry non-canonical kinetic terms whose normalization is set by a coupling function that depends on an accompanying modulus field. As dark matter, such an axion forms a cold condensate whose…