Paper List

Paperlist

• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• Generalizable Person Re-identification via Balancing Alignment and Uniformity
• Rethinking Graph Masked Autoencoders through Alignment and Uniformity
• Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations
• Geodesic Multi-Modal Mixup for Robust Fine-Tuning
• Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation
• uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering
• It’s Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
• Debiased Contrastive Learning of Unsupervised Sentence Representations
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• Toward Human-AI Alignment in Large-Scale Multi-Player Games
• Graph-based Alignment and Uniformity for Recommendation
• The Role of Local Alignment and Uniformity in Image-Text Contrastive Learning on Medical Images
• Feature Alignment and Uniformity for Test Time Adaptation
• Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems
• Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels
• Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation
• Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation
• Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
• Training language models to follow instructions with human feedback
• Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing
• Whose Opinions Do Language Models Reflect?
• Whitening Sentence Representations for Better Semantics and Faster Retrieval
• Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
• Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation
• Aligning Large Multimodal Models with Factually Augmented RLHF
• RAIN: Your Language Models Can Align Themselves without Finetuning
• Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models
• RotoGrad: Gradient Homogenization in Multitask Learning
• Dual Distribution Alignment Network for Generalizable Person Re-Identification
• Improving neural network representations using human similarity judgments
• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
• ControlRec: Bridging the Semantic Gap between Language Model and Personalized Recommendation
• On the Sentence Embeddings from Pre-trained Language Models
• Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
• Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment
• CyCLIP: Cyclic Contrastive Language-Image Pretraining
• Chain of Hindsight Aligns Language Models with Feedback
• Rethinking The Uniformity Metric in Self-Supervised Learning
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts
• Align on the Fly: Adapting Chatbot Behavior to Established Norms
• RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
• Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model
• Towards the Generalization of Contrastive Self-Supervised Learning
• Unsupervised Learning by Predicting Noise
• IterAlign: Iterative Constitutional Alignment of Large Language Models
• Zephyr: Direct Distillation of LM Alignment
• Perfect Alignment May be Poisonous to Graph Contrastive Learning
• Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
• LIMA: Less Is More for Alignment
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Understanding the Behaviour of Contrastive Loss
• DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
• Training Socially Aligned Language Models on Simulated Social Interactions
• Self-Instruct: Aligning Language Models with Self-Generated Instructions
• Preference Ranking Optimization for Human Alignment
• Human alignment of neural network representations
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• LiT: Zero-Shot Transfer with Locked-image text Tuning
• As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making
• The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
• Improving alignment of dialogue agents via targeted human judgements
• ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference
• RRHF: Rank Responses to Align Language Models with Human Feedback without tears
• Investigating Uncertainty Calibration of Aligned Language Models under the Multiple-Choice Setting
• Uniform Learning in a Deep Neural Network via “Oddball” Stochastic Gradient Descent
• Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
• ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
• Representation Learning with Large Language Models for Recommendation
• Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
• Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
• RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
• Towards Reliable Alignment: Uncertainty-aware RLHF
• FLAVA: A Foundational Language And Vision Alignment Model
• Criticality versus uniformity in deep neural networks
• OpenAssistant Conversations – Democratizing Large Language Model Alignment
• Generative Judge for Evaluating Alignment
• LLaRA: Large Language-Recommendation Assistant
• In conversation with Artificial Intelligence: aligning language models with human values
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Aligning AI With Shared Human Values
• Human-Instruction-Free LLM Self-Alignment with Limited Samples
• The Wisdom of Hindsight Makes Language Models Better Instruction Followers
• Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior
• ValueCompass: A Framework of Fundamental Values for Human-AI Alignment
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Unified Deep Supervised Domain Adaptation and Generalization
• A General Language Assistant as a Laboratory for Alignment
• Learning Human-like Representations to Enable Learning Human Values
• Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
• Specific versus General Principles for Constitutional AI
• Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
• RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
• Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
• Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
• Doubly Stochastic Neighbor Embedding on Spheres
• RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models’ Alignment
• Self-Alignment with Instruction Backtranslation
• What are human values, and how do we align AI to them?
• Getting aligned on representational alignment
• Designing for Human-Agent Alignment: Understanding what humans want from their agents
• Alignment with human representations supports robust few-shot learning
• Cooperative Inverse Reinforcement Learning
• Reward Design with Language Models
• Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
• TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
• Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• CommunityLM: Probing Partisan Worldviews from Language Models