1 citations · 1 across the 17 of their papers we have counts for
19 papers
Early Learning Shapes Later Directions Of Representation Change In Continual Learning
Yuantao Deng, Jinnuo Liu, Kaizhen Tan +1
Representations continually change as a network learns new tasks. We ask whether early representational changes naturally form a geometric structure that continues to shape later l…
PopNavShift: Stress-Testing Social Navigation under Behavioral Population Shift
Kaizhen Tan, Diyu Zheng, Tim Guangyu Wu +1
Social-navigation algorithms are often evaluated under a fixed pedestrian-behavior distribution, despite substantial variation in pedestrian responses to robots across individuals…
Seeing the City or Recognizing the Place? What Street-View Imagery Adds Beyond Existing Urban Data in VLM-Based Urban Sensing
Kaizhen Tan
Street-view imagery is increasingly analysed with vision-language models (VLMs) to infer urban attributes, but predictive accuracy alone does not show how much a photograph contrib…
Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning
Kaizhen Tan, Yang Feng, Heqing Du +3
Metric questions about video, such as the speed of a moving object, require a vision-language model to convert visual measurements into physical units using a real-world reference…
You Cannot Photograph the Same Street Twice: Reliability Limits in Vision-Language Measurement of Urban Change
Kaizhen Tan
Vision-language models (VLMs) are increasingly used to measure urban change from repeated street-level imagery, and the results are often mapped for individual sample points. Such…
Vision Models Predict Urban Scene Appraisal with Limited Neural Alignment
Kaizhen Tan, Yuantao Deng
Pretrained vision embeddings are widely used to model how people appraise urban scenes, and they are validated almost entirely by how well they predict human ratings. Accurate pred…
Beyond Multimodal Alignment: Shared Physical Representations Across Sensors and Action Orders
Kaizhen Tan, Xin Xu, Siru Tao +4
Multimodal world models are often evaluated by whether different sensors produce similar representations. However, similar representations do not necessarily imply that the models…
Renaming or Tightness: Enforcing Disjunctive Information Flow Policies
Xin Xu, Siru Tao, Kaizhen Tan
A disjunctive policy allows a value to depend on at most one of two secrets and never on both: an analyst may consult one client's file or the other's, a share of a split secret ma…
What Can Latent World Models Know? Physical Information in Multimodal Predictive Representations
Kaizhen Tan, Sizhe Xu, Xin Xu +6
A central premise of latent world models is that predicting the future encourages representations to internalize the physics of their environment. We ask which physical quantities…
Collusion with Competitive Marginals: Price-Level Audits Are Blind by Construction
Xin Xu, Chengrui Wu, Jiayu Lu +3
Empirical work on algorithmic collusion asks one question of the data: are prices supracompetitive? We show this can be answered "no" by a conspiracy that is nonetheless profitable…
Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks
Xin Xu, Siru Tao, Kaizhen Tan
A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit. It cannot do otherwise:…
How Much Can a LoRA Adapter Memorize? Measuring Adapter Capacity in Bits
Kaizhen Tan, Heqing Du, Yang Feng
LoRA adapters are often shared on their own, and the amount of information they can hold about their training data bounds what sharing them can reveal. Following Morris et al. (202…
GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity in Text-to-Image Street-View Generation
Kaizhen Tan, Hanzhe Hong, Siru Tao
Text-to-image models can generate plausible street scenes from prompts such as "a street in New York City," but it remains unclear whether these images resemble the requested place…
CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference
Kaizhen Tan, Rong Gu, Mingyuan Li
Retrieval-Augmented Generation (RAG) improves factual grounding, but it also lengthens prompts and raises prefill cost. Prefix caching in serving engines such as vLLM reduces this…
Confidence under Visual Token Pruning: Removed Evidence and Risk-Controlled Token Budgets for MLLMs
Kaizhen Tan, Yang Feng, Heqing Du +3
Visual token pruning speeds up multimodal large language models (MLLMs) by keeping a small subset of the visual tokens, and pruning methods are compared by the accuracy they retain…
CREG: Compass Relational Evidence Graph for Characterizing Directional Structure in VLM Spatial-Reasoning Attribution
Kaizhen Tan, Yang Feng, Heqing Du
Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized by the queried spatial relation o…
A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks
Weihua Huan, Kaizhen Tan, Xintao Liu +4
Traffic congestion propagation poses significant challenges to urban sustainability, disrupting spatial accessibility. The cascading effect of traffic congestion propagation can ca…
Multimodal Deep Learning for ATCO Command Lifecycle Modeling and Workload Prediction
Kaizhen Tan
Air traffic controllers (ATCOs) issue high-intensity voice commands in dense airspace, where accurate workload modeling is critical for safety and efficiency. This paper proposes a…
Decoding Tourist Perception in Historic Urban Quarters with Multimodal Social Media Data: An AI-Based Framework and Evidence from Shanghai
Kaizhen Tan, Yufan Wu, Yuxuan Liu +1
Historic urban quarters are increasingly shaped by tourism and lifestyle consumption, yet planners often lack scalable evidence on what visitors notice, prefer, and criticize in th…