research note
This paper addresses a gap in role-playing agents: most systems can imitate a character’s style from text, but they remain weak at using visual scene context to modulate tone, tension, and situatio…
research note
SEI-SHIELD tackles a practical weakness in specific emitter identification: deep SEI models can look strong on clean data yet collapse when training labels are noisy due to channel ambiguity, annot…
research note
This paper presents an eight-week longitudinal observational study comparing four frontier LLM families (GPT, Gemini, Grok, Claude) on one-shot single-file HTML/CSS/JavaScript generation tasks
research note
This paper tackles a long-standing bootstrapping problem in QKD: the classical channel must be authenticated, but standard information-theoretic authentication usually needs a pre-shared secret, wh…
research note
Vol-Mark targets a practical gap in medical watermarking: most prior methods either operate on 2D slices or sacrifice exact recoverability, even though telemedicine increasingly exchanges full 3D C…
research note
This paper addresses a critical blind spot in agentic browser security research: while prior work focused exclusively on indirect prompt injection (explicit adversarial instructions embedded in pag…
research note
This paper tackles a real modeling bottleneck in superconducting cQED: once Josephson nonlinearities and structured dissipation both matter, the usual Born-Markov master-equation workflow either be…
research note
This is a survey paper rather than an empirical model paper, so its contribution is conceptual synthesis: it organizes the fast-growing audio-visual intelligence (AVI) literature under a unified fr…
research note
This paper addresses the challenging problem of sampling from complex, unnormalized multimodal distributions when density evaluations are costly
research note
dtour addresses a persistent gap in high-dimensional data visualization: any single 2D projection of a p-dimensional dataset discards all structure orthogonal to the chosen projection plane, yet ex…
research note
This paper tackles a very practical bottleneck in digital quantum simulation: how to run large, long-time Fermi-Hubbard dynamics on real hardware without the circuit cost and noise overwhelming the…
research note
Flow Sampling is a diffusion-style sampler for unnormalized target densities when you can evaluate the energy or reward gradient but you do not have target samples
