⚙️ Model Training - Bingran · Scour

Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?

🧠AI Research Academic

ViP-VL: Vietnamese Self-supervised Speech Pretraining Model with Vector-Quantization Learning

💬LLMs Academic

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model

🔄Transformers Academic

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

📐Scaling Laws Academic

Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching

💬LLMs Academic

Emergence of Context Characteristics Sensitivity in Large Language Models

🎮Reinforcement Learning Academic

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

💬LLMs Academic

Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent

📉Deep Learning Academic

Stage-1 Controls the Entropy Regime, Not the Outcome

🎮Reinforcement Learning Academic

On the Geometry of On-Policy Distillation

🎮Reinforcement Learning Academic

Harness In-Context Operator Learning with Chain of Operators

💬LLMs Academic

In-Context Learning for Latent Space Bayesian Optimization

💬LLMs Academic

Pretraining Recurrent Networks without Recurrence

📉Deep Learning Academic

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

🎮Reinforcement Learning Academic

A Unifying Lens on Reward Uncertainty in RLHF

🎮Reinforcement Learning Academic

Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data

💬LLMs Academic

Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks

📉Deep Learning Academic

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

💬LLMs Academic

World Pilot: Steering Vision-Language-Action Models with World-Action Priors

💬LLMs Academic

From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning

🧠AI Research Academic

Log in to enable infinite scrolling