Found 247,085 document(s)
Page 68 of 16473
-
While aligned large language models (LLMs) can successfully complete many creative tasks, their outputs tend to be highly self-similar. Though solutions to this problem of "mode collapse" have been proposed, comprehensiv...
-
Chirality-induced spin selectivity can enable spin generation by nonmagnetic junctions, but its symmetry requirements remain debated. We show that the symmetry of the junction constrains its polarizing behavior: a spin p...
-
Movable and rotatable-antenna systems treat element placement as a design resource, but the supporting theory is largely position-only. We prove that element orientation is an effective spatial resource in its own right,...
-
Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for training reasoning models, but its computational cost makes efficient data selection increasingly important. Since training ex...
-
LLM agents are widely used for software development and debugging, but their adoption in embedded systems, especially for wireless tasks, remains limited. This is because embedded development requires hardware-in-the-loo...
-
User simulators can help evaluate and train AI systems to interact with humans at scale. To do so, evaluation of user simulators must measure behavioral parity with people. We evaluate whether memory-constrained user sim...
-
Generating time-to-event data is increasingly important in survival analysis, but it remains statistically challenging because event times are often censored and thus prevent flexible generative modeling. To fill this ga...
-
With advancements in learning-based policies, robots are increasingly being deployed in human-centric environments, such as manufacturing floors and homes, where safe and precise operation requires compensating for unkno...
-
Preserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive ReplayReinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capabilities of large language models, but often reduces the diversity of their reasoning behaviors. We study this phenomenon from the perspect...
-
Immersive virtual reality (VR) adaptations of neuropsychological tests change how a test operates. Before their scores are interpreted, the individuals they are intended to assess should find them usable, acceptable and ...
-
While the Pepper's Ghost illusion is a 19th-century optical technique, we found that this forgotten gimmick exposes vulnerabilities in modern face recognition systems. This paper introduces the 'Ghost Attack': a physical...
-
We empirically analyze two recently proposed encoder-free multimodal LLMs, Gemma-4 12B and Inkling-Small. Unlike previous multimodal LLMs, these models do not use modality-specific encoders to extract tokenized embedding...
-
We aim to design revenue-maximizing single-item auctions that are deterministic, strategy-proof, and ex post individually rational --- the quintessential fundamental model for optimal mechanism design. While Myerson's se...
-
This work demonstrates the use of a fast simulation-based training framework to learn control policies using reinforcement learning. The hardware requirements are minimal and the simulation-learned policies transfer reli...
-
This paper considers nonlinear digital self-interference (SI) cancellation and uplink-channel estimation for single-antenna in-band full-duplex radios when a desired uplink pilot is present during SI training. In this se...