research note
AmbiSuR addresses a specific failure mode in Gaussian-splatting surface reconstruction: when photometric supervision is ambiguous or incomplete, optimization can converge to overblown primitives, r…
research note
This paper addresses the challenges in training Sparse Mixture-of-Experts (SMoE) models, focusing specifically on the routing mechanism that assigns tokens to experts
research note
This paper presents a comprehensive systematic review of the challenges and emerging solutions in sign language recognition (SLR) and translation (SLT) for low-resource languages, illustrated throu…
research note
Attractor Models are proposed as an alternative to standard looped Transformers for iterative refinement in language modeling and reasoning
research note
This paper addresses a core limitation in language-based interactive environments—such as web browsers, code terminals, and text-based simulators—which emit raw textual observations but provide no …
research note
This paper studies a simple but important problem: how to make dense embedding models behave more like flexible instruction-following systems on zero-shot search and classification tasks, without p…
research note
DR-Gym addresses a gap in reinforcement-learning environments for demand response at the electric-utility level
research note
This paper studies whether large language models can be used to generate SQL injection payloads that evade modern defenses, and it does so as a benchmarking paper rather than a single-model demo
research note
Survey Footprint Explorer is a browser-only application for visualizing and comparing sky coverage regions for major astronomical imaging surveys, and for testing whether catalogued sources fall in…
research note
This paper addresses the challenge of verifying and reusing AI-generated content (AIGC) reliably in the emerging Agentic Web, where autonomous AI agents generate and reuse content extensively
research note
MiRA is a browser-based visualization tool for biological multilayer networks, aimed at a gap the authors see between strong multilayer analysis methods and weak interactive visualization support
research note
Traffic state estimation (TSE) from sparse fixed freeway sensors is fundamentally difficult for physics-informed neural networks (PINNs) because the Lighthill-Whitham-Richards (LWR) model—a first-o…
