Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhenyu Yu

Zhenyu Yu

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Info Retrieval×5Crypto×2NLP×1

Frequent co-authors

Shuigeng Zhou5×
Jihong Guan2×

Research Timeline

2026
When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction

The paper introduces MeRa, a metric-space bias module, demonstrating that latent reasoning only improves spatial prediction when it is explicitly grounded in the underlying metric space.

MARS: Multi-rate Aggregation of Recency Signals for Sequential Recommendation across Sparse and Dense Regimes

MARS proposes an encoder-agnostic aggregation operator that explicitly models multi-scale temporal structure in sequential recommendation, achieving state-of-the-art performance across both sparse and dense data regimes.

Ghost: Plausible Yet Unlearnable Trajectories via On-Manifold Substitution for Next-POI Privacy

Ghost introduces a manifold-aligned framework to generate plausible yet unlearnable synthetic check-in trajectories, significantly degrading the accuracy of next-POI prediction models without sacrificing realism.

Ghost: Plausible Yet Unlearnable Trajectories via On-Manifold Substitution for Next-POI Privacy

Ghost introduces a manifold-aligned framework to generate plausible, unlearnable synthetic check-in trajectories that significantly degrade an attacker's ability to predict future locations.

Caliper: Probing Lexical Anchors versus Causal Structure in LLMs

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.IRRecentJun 3, 2026

Caliper: Probing Lexical Anchors versus Causal Structure in LLMs

Zhenyu Yu, Shuigeng Zhou

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.

View →
cs.IRRecentJun 2, 2026

When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction

Zhenyu Yu, Shuigeng Zhou

The paper introduces MeRa, a metric-space bias module, demonstrating that latent reasoning only improves spatial prediction when it is explicitly grounded in the underlying metric space.

View →
cs.IRRecentJun 2, 2026

MARS: Multi-rate Aggregation of Recency Signals for Sequential Recommendation across Sparse and Dense Regimes

Zhenyu Yu, Shuigeng Zhou

MARS proposes an encoder-agnostic aggregation operator that explicitly models multi-scale temporal structure in sequential recommendation, achieving state-of-the-art performance across both sparse and…

View →
cs.CRcs.IRRecentJun 2, 2026

Ghost: Plausible Yet Unlearnable Trajectories via On-Manifold Substitution for Next-POI Privacy

Zhenyu Yu, Jihong Guan, Shuigeng Zhou

Ghost introduces a manifold-aligned framework to generate plausible yet unlearnable synthetic check-in trajectories, significantly degrading the accuracy of next-POI prediction models without sacrific…

View →
cs.CRcs.IRRecentJun 2, 2026

Ghost: Plausible Yet Unlearnable Trajectories via On-Manifold Substitution for Next-POI Privacy

Zhenyu Yu, Jihong Guan, Shuigeng Zhou

Ghost introduces a manifold-aligned framework to generate plausible, unlearnable synthetic check-in trajectories that significantly degrade an attacker's ability to predict future locations.

View →