arXiv subjects

Shihao Ding

Publications and source records attributed to Shihao Ding.

4 recordsLinked to original sources

arXiv2026

Personalizing LLM Agent Memory Using Biometrics

Personalized memory helps LLM agents deliver stable, tailored assistance by storing and reusing user-specific data across interactions. In multi-user scenarios, however, retrieval must consider not only semantic similarity but also whether the current requester matches the identity associated with the stored memory. We propose Bio-Memory, a biometric-aware memory architecture that conditions memory retrieval on both semantic similarity and biometric matching. Built on top of A-Mem, Bio-Memory augments each atomic memory note with a biometric embedding and uses biometric matching to form the retrieval candidate pool before semantic ranking. We evaluate Bio-Memory on LoCoMo in a 10-user shared-agent setting over 7 face benchmarks and 10 palmprint protocols. Across datasets, Bio-Memory consistently separates owner and non-owner queries. Under face-based personalization, the largest average gap reaches 27.29% / 21.15% in F1 / BLEU-1 on CALFW; under palmprint-based personalization, the corresponding gap is 25.75% / 19.22% on MS_Blue. These results support biometrics as a practical control signal for personalized memory retrieval in shared environments.

cs.AI↗

arXiv2026

BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents

KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however, reusable KV blocks introduce a missing access-control question: semantic relevance alone cannot determine whether a memory block is authorized for the current physical user. We propose Bio-MemArt, a biometric-aware KV-cache memory framework for multi-user LLM agents. Bio-MemArt attaches a normalized biometric template to each stored KV memory block, filters the shared memory pool with the current user's biometric probe, and then runs the original MemArt retrieval and KV reuse pipeline only inside the authorized candidate pool. This design preserves latent-space retrieval, direct cache reuse, and decoupled position encoding while adding physical-user access control to shared KV memory. We evaluate Bio-MemArt under Owner and Non-owner query conditions on long-term dialogue QA with face and palmprint benchmarks. Across face benchmarks, the average owner and non-owner biometric success rates are 95.71% and 0.86%; across palmprint benchmarks, they are 97.60% and 2.00%. In the efficiency study, average prefill tokens drop from 18,781.96 under full-context prompting to 28.57 with Bio-MemArt, showing that biometric gating preserves the low-token operating regime of KV-cache memory.

cs.AI↗

arXiv2023

Unveiling the dynamical diversity of quantum dot lasers subject to optoelectronic feedback

This paper investigates experimentally and numerically the nonlinear dynamics of an epitaxial quantum dot laser on silicon subjected to optoelectronic feedback. Experimental results showcase a diverse range of dynamics, encompassing square wave patterns, quasi-chaotic states, and mixed waveforms exhibiting fast and slow oscillations. These measurements unequivocally demonstrate that quantum dot lasers on silicon readily and stably generate a more extensive repertoire of nonlinear dynamics compared to quantum well lasers. This pronounced sensitivity of quantum dot lasers to optoelectronic feedback represents a notable departure from their inherent insensitivity to optical feedback arising from reflections. Moreover, based on the Ikeda-like model, our simulations illustrate that the inherent characteristics of quantum dot lasers on silicon enable rapid and diverse dynamic transformations in response to optoelectronic feedback. The emergence of these exotic dynamics paves the way for further applications like integrated optical clocks, optical logic, and optical computing.

physics.optics↗

arXiv2023

Broadband amplitude squeezing in electrically driven quantum dot lasers

The generation of broadband squeezed states of light lies at the heart of high-speed continuous-variable quantum information. Traditionally, optical nonlinear interactions have been employed to produce quadrature-squeezed states. However, the harnessing of electrically pumped semiconductor lasers offers distinctive paradigms to achieve enhanced squeezing performance. We present evidence that quantum dot lasers enable the realization of broadband amplitude-squeezed states at room temperature across a wide frequency range, spanning from 3 GHz to 12 GHz. Our findings are corroborated by a comprehensive stochastic simulation in agreement with the experimental data.

physics.optics↗