⚙️ Model Training - Bingran · Scour

Breaking the Ice: Analyzing Cold Start Latency in vLLM

🖥️ML Systems Academic

arxiv.org··Hacker News

Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models

💬LLMs Academic

Multilingual Sentiment Aware Text Summarization A Reinforcement Learning Approach for Consistency Maintenance

🎮Reinforcement Learning Academic

On Subquadratic Architectures: From Applications to Principles

📐Scaling Laws Academic

The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

📐Scaling Laws Academic

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning

🔄Transformers Academic

Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning

📐Scaling Laws Academic

Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data

💬LLMs Academic

Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails

💬LLMs Academic

Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families

💬LLMs Academic

SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration

🔍Interpretability Academic

Reinforcement Learning for Flow-Matching Policies with Density Transport

🎮Reinforcement Learning Academic

APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies

💬LLMs Academic

PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training

💬LLMs Academic

SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning

🎮Reinforcement Learning Academic

Predictive Coding with Bayesian Priors via Proximal Gradients

📉Deep Learning Academic

SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

🔄Transformers Academic

FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

🎮Reinforcement Learning Academic

RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning

📉Deep Learning Academic

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks

📐Scaling Laws Academic

No more posts from Bingran's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Sign up or log in to see more results

Log in to enable infinite scrolling