💬 Natural Language Processing - jhcha.oyo · Scour

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output

🎯RLHF Academic

Annotation of Positive vs Negative User Interactions for Social Sign Prediction

📝NLP Academic

A Unifying Lens on Reward Uncertainty in RLHF

🎯RLHF Academic

Hidden Consensus:Preference-Validity Compression in Human Feedback

🎯Fine-Tuning Academic

Phase transition in large language models and the criticality of natural languages

🤖AI Academic

LLMCodec: Adapting Video Codecs for Efficient Weight Compression of Large Language Models

💬LLMs Academic

Beyond Patches: Superpixel Token-based Transformers for Attribute-Specific Fashion Retrieval

🤖AI Academic

When Vision Misleads, Let Location Speak: A Worldwide Image Geo-Localization Method via Location Attention Mechanism and Large Multimodal Models

🤖AI Academic

Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair

🤖AI Academic

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

🤖AI Academic

Zero and Few Shot Load Forecasting with Large Language Models

🧠Deep Learning Academic

What Do People Actually Want From AI? Mapping Preference Plurality

🎯RLHF Academic

GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention

🤖AI Academic

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

🎛️Fine-tuning Academic

Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling

🎯RLHF Academic

Causal Semantic Alignment for LLM-based Time Series Forecasting

🤖AI Academic

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)

💬LLMs Academic

TeamHerald@CHIPSAL 2026: Hate Speech Detection and Sentiment Analysis of Nepali Memes using Transformer-based Architectures and Ensemble Learning

📝NLP Academic

GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection

🤖AI Academic

"Chi nas dal soch el sent de legn" -- Auditing Text Corpora for Lombard

📝NLP Academic

Log in to enable infinite scrolling