Searcharxiv⌕ Search

arXiv subjects

Hongji Li

Publications and source records attributed to Hongji Li.

24 records · Page 2Linked to original sources

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and by leveraging large-scale unlabeled data via pseudo-label distillation. However, existing methods that rely on global depth normalization treat all depth values equally, which can amplify noise in pseudo-labels and reduce distillation effectiveness. In this paper, we present a systematic analysis of depth normalization strategies in the context of pseudo-label distillation. Our study shows that, under recent distillation paradigms (e.g., shared-context distillation), normalization is not always necessary, as omitting it can help mitigate the impact of noisy supervision. Furthermore, rather than focusing solely on how depth information is represented, we propose Cross-Context Distillation, which integrates both global and local depth cues to enhance pseudo-label quality. We also introduce an assistant-guided distillation strategy that incorporates complementary depth priors from a diffusion-based teacher model, enhancing supervision diversity and robustness. Extensive experiments on benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.

cs.CV↗

Teach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration

The surge in multimedia content has led to the development of Multi-Modal Recommender Systems (MMRecs), which use diverse modalities such as text, images, videos, and audio for more personalized recommendations. However, MMRecs struggle with noisy data caused by misalignment among modal content and the gap between modal semantics and recommendation semantics. Traditional denoising methods are inadequate due to the complexity of multi-modal data. To address this, we propose a universal guided in-sync distillation denoising framework for multi-modal recommendation (GUIDER), designed to improve MMRecs by denoising user feedback. Specifically, GUIDER uses a re-calibration strategy to identify clean and noisy interactions from modal content. It incorporates a Denoising Bayesian Personalized Ranking (DBPR) loss function to handle implicit user feedback. Finally, it applies a denoising knowledge distillation objective based on Optimal Transport distance to guide the alignment from modality representations to recommendation semantics. GUIDER can be seamlessly integrated into existing MMRecs methods as a plug-and-play solution. Experimental results on four public datasets demonstrate its effectiveness and generalizability. Our source code is available at https://github.com/Neon-Jing/Guider

cs.IR↗

Evaluating the Effect of Audience in a Virtual Reality Presentation Training Tool

Public speaking is an essential skill in everyone's professional or academic career. Nevertheless, honing this skill is often tricky because training in front of a mirror does not give feedback or inspire the same anxiety as present-ing in front of an audience. Further, most people do not always have access to the place where the presentation will happen. In this research, we developed a Virtual Reality (VR) environment to assist in improving people's presentation skills. Our system uses 3D scanned people to create more realistic scenarios. We conducted a study with twelve participants who had no prior experience with VR. We validated our virtual environment by analyzing whether it was preferred to no VR system and accepted regardless of the existence of a virtual audience. Our results show that users overwhelmingly prefer to use the VR system as a tool to help them improve their public speaking skills than training in an empty environment. However, the preference for an audience is mixed.

cs.HC↗

1305 nm MoTe2-on-silicon Laser

The missing piece in the jigsaw of silicon photonics is a light source that can be easily incorporated into the standard silicon fabrication process. Recent advances in the development of atomically thin layers of semiconducting transition metal dichalogenides (TMDs), with direct bandgaps in the near-infrared region, have opened up new possibilities for addressing this need. Here, we report a unique silicon laser source that employs molybdenum ditelluride (MoTe2) as a gain material in a photonic crystal nanocavity resonator, fabricated in silicon-on-insulator. We demonstrate optically pumped MoTe2-on-silicon devices lasing at 1305 nm, i.e. in the centre of the O-band used in optical communications, operating in the continuous-wave (CW) regime, at room temperature and with a threshold power density as low as 1.5 kW/cm2. This 2D-on-silicon geometry offers the promise of an integrated low-cost electrically pumped nanoscale silicon light source, thereby adding an essential building block to the silicon photonics platform.

cond-mat.mes-hall↗

Femtosecond soliton diode on heterojunction Bragg-grating structure

We numerically propose a scheme for realizing an all-optical femtosecond soliton diode based on a tailored heterojunction Bragg grating, which is designed by two spatially asymmetric chirped cholesteric liquid crystals. Our simulations demonstrate that with the consideration of optical nonlinearity, not only the femtosecond diode effect with nonreciprocal transmission ratio up to 120 can be achieved, but also the optical pulse evolving into soliton which maintains its shape during propagation through the sample is observed. Further, the influence of pulse width and the carrier wavelength to the femtosecond diode effect is also discussed in detail. Our demonstrations might suggest a new direction for experimentally realizing the femtosecond soliton diode based on the cholesteric liquid crystals.

physics.optics↗

Slow-light all-optical soliton diode based on tailored Bragg-grating structure

An all optical soliton diode (AOSD) is proposed based on a sandwich nonlinear Bragg-grating structure: a linearly chirped Bragg-grating linked to a uniform Bragg-grating and again to a chirped Bragg-grating. The nonreciprocity is achieved by introducing two spatially asymmetric chirped Bragg-gratings with optical nonlinearity. High transmission ratio up to 150 is obtained when launching a picosecond Gaussian pulse into the setting. We find that such pulses in a form of solitons propagate at a rather small velocity ($<0.03c$) when pulse wavelength is selected in the vicinity of photonic bandgap.

physics.optics↗