AI research papers

Publications on agents, large language models, recommender systems, multimodal AI, and finance. Each record keeps the citation, research links, and related work together on a stable internal URL.

SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment

GIFT: LLM-Guided State-Reward Interface for Financial Reinforcement Learning

Benchmarking Multimodal Large Language Models for Missing Modality Completion in Product Catalogues

Bridging NIP and MLM: A Unified Meta-Learning Framework for Sequential Recommendation

EVE-Bench: Entropy-Guided Benchmarking and Evaluation for Frontier Video Generation Models

From Proxy IV to Generative IV: Causal Inference via Latent Structure Learning

Interpretable Knowledge Tracing via Explicit-Implicit Alignment

LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-Video Generation

On the Role of Language Representations in Auto-Bidding: Findings and Implications

PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models

Token Bayesian Optimization: Reasoning LLMs Think Better with the Right Length

AMBER: Adaptive Meta Balanced Paradigm for Heterogeneous Graph-Based Knowledge Tracing

Bridging the Gap: Teacher-Assisted Wasserstein Knowledge Distillation for Efficient Multi-Modal Recommendation

ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting

Crossan: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation

Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation

Frequency-Decoupled Distillation for Efficient Multimodal Recommendation

Machine Behaviorism: Exploring the Behavioral Dynamics of Large Language Models in Decision Making

Mitigating Data Sparsity with Self-Supervised Contrastive Diffusion for Mamba-based Sequential Recommendation

PGT-PO: Plackett-Gumbel-Triplet Enhanced LLM for Preference Optimization in Machine Translation

SOLAR: Serendipity Optimized Language Model Aligned for Recommendation

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

Uncertainty-Aware Knowledge Tracing

A Comprehensive Review of Community Detection in Graphs

An Empirical Study of Training ID-Agnostic Multi-Modal Sequential Recommenders