Paper Presentation Details

You can either collaborate with a team or present individually. The choice of topic is entirely up to you.

  • Introduction and Background – What is the general impact and background of the topic?
  • Motivation and Problem – What is the core research problem, and why do we study it?
  • Related Work and Challenges – How did previous works address this problem, and what are some of the challenges?
  • Proposed Solutions/Methods and Rationale – What are the proposed methods/techniques, and why are they proposed? What specific reasons that solving this problem would require these proposed(1) methods/techniques？
  • Experimental Setting, Results, and Analysis – What experiments are designed to verify the proposed method? How are results being discussed and analyzed? Are there any interesting findings?
  • Conclusion and Future Work

Generative Models

RAG Systems

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs [Paper]
LLM Alignment as Retriever Optimization: An Information Retrieval Perspective [Paper]
RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation [Paper]
Wikipedia Contributions in the Wake of ChatGPT [Paper]
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective [Paper]

Agentic AI

HETEROGENEOUS SWARMS: Jointly Optimizing Model Roles and Weights for Multi-LLM System [Paper]
OASIS: Open Agents Social Interaction Simulations on One Million Agents [Paper]
Why Do Multi-Agent LLM Systems Fail? [Paper]
A Multi-LLM Debiasing Framework [Paper]
TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System [Paper]
Preference Leakage: A Contamination Problem in LLM-as-a-judge [Paper]
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks [Paper]
GPTSwarm: Language Agents as Optimizable Graphs [Paper]

Neural-Symbolic Learning

Self-Discover: Large Language Models Self-Compose Reasoning Structures [Paper]
ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs [Paper]
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [Paper]
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis [Paper]

Complex Topology and Graph Structure

PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph [Paper]
Slow Perception: Let’s Perceive Geometric Figures Step-by-step [Paper]
Representation Learning of Geometric Trees [Paper]
Deep Identification of Propagation Trees [Paper]
Network Tomography with Path-Centric Graph Neural Network [Paper]