Latest Research
Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space
We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space.
Language Fairness in Multilingual Information Retrieval
We also evaluate real MLIR systems on two publicly available benchmarks and show that the PEER scores align with prior analytical findings on MLIR fairness.
LocInv: Localization-aware Inversion for Text-Guided Image Editing
Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts.
Lying Graph Convolution: Learning to Lie for Node Classification Tasks
In this paper, we introduce Lying-GCN, a new DGN inspired by opinion dynamics that can adaptively work in both the heterophilic and the homophilic setting.
Modeling Activity-Driven Music Listening with PACE
While the topic of listening context is widely studied in the literature of music recommender systems, the integration of regular user behavior is often omitted.
S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
safamessaoud/s2ac-energy-based-rl-with-stein-soft-actor-critic
•
•
We derive a closed-form expression of the entropy of such policies.
Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
Based on this network, a two-stage purification approach is naturally developed.
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs.
The Importance of Model Inspection for Better Understanding Performance Characteristics of Graph Neural Networks
This study highlights the importance of conducting comprehensive model inspection as part of comparative performance analyses.
Analyzing the Role of Semantic Representations in the Era of Large Language Models
We find that it is difficult to predict which input examples AMR may help or hurt on, but errors tend to arise with multi-word expressions, named entities, and in the final inference step where the LLM must connect its reasoning over the AMR to its prediction.
