A.J.A. Jubayer Talukder

xubayer

·

AI & ML interests

None yet

Recent Activity

updated a Space 16 days ago

xubayer/repro-reward-free-alignment-for-conflicting-objectives

published a Space 16 days ago

xubayer/repro-reward-free-alignment-for-conflicting-objectives

updated a Space 16 days ago

xubayer/repro-on-structured-state-space-duality

View all activity

Organizations

xubayer 's Spaces 13

Reproduction: Reward-free Alignment for Conflicting Objectives

Explore project logs, traces, and workspace with agent collaboration

Reproduction: On Structured State-Space Duality

Explore project logs, traces, and workspace in a single view

Reproduction: Attention's forward pass and Frank-Wolfe

Explore logs, view code/traces, and collaborate with an AI agent

Reproduction: A Tight Theory of Error Feedback Algorithms in Distributed Optimization

Explore project logbook with code, traces, and AI collaboration

Reproduction: Measuring Agents in Production

Explore project logs, traces, and workspace in an interactive web UI

Reproduction: Ski Rental with Distributional Predictions of Unknown Quality

Explore research logbooks and collaborate with a coding agent

Reproduction: Who Said Neural Networks Aren't Linear?

Explore and share experiment logs with an interactive UI

Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Explore experiment logs, traces, and workspace in a unified view

Iep Generator

Generate personalized IEP drafts from student assessment data

LlamaPIE Dual Inference CPU

LlamaPIE pipeline (1B Classifier + 8B Generator in GGUF form

LlamaPIE Dual Inference CPU

LlamaPIE pipeline (1B Classifier + 8B Generator in GGUF form

LlamaPIE Dual Inference CPU

LlamaPIE pipeline (1B Classifier + 8B Generator in GGUF form

LlamaPIE-Dual-Inference 1

LlamaPIE is explicitly a two-model pipeline (small “when to