Running
Reproduction: Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
🎯
Explore code, traces, and workspace in an interactive logbook
Biswaranjan Samal
visv-Bro
·
AI & ML interests
Inference, Post training, Pretraining. Statistics
Recent Activity
updated a Space 1 day ago
visv-Bro/repro-reward-shaping-for-inference-time-alignment-a-stackelberg-game-perspective published a Space 1 day ago
visv-Bro/repro-reward-shaping-for-inference-time-alignment-a-stackelberg-game-perspective updated a Space 1 day ago
visv-Bro/repro-improved-stochastic-optimization-of-logsumexpOrganizations
Running
Reproduction: Improved Stochastic Optimization of LogSumExp
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: The Catastrophic Failure of the k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It
🎯
Explore code logs, traces, and workspace in an interactive web logbook
Running
Reproduction: Causal Matrix Completion under Multiple Treatments via Mixed Synthetic Nearest Neighbors
🎯
Explore and manage research code, traces, and workspace
Running
Reproduction: Mirror Descent Under Generalized Smoothness
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
🎯
Explore and manage project logs, code traces, and workspace
Running
Reproduction: Conditional Coverage Diagnostics for Conformal Prediction
🎯
Explore code logs, traces, and workspace in a web logbook
Running
Reproduction: Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport
🎯
View logs and collaborate with your coding agent
Running
Reproduction: On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models
🎯
Browse code logs and trace data in an interactive web logbook
Running
Reproduction: Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
🎯
Explore experiment logs and collaborate with an AI agent
Running
Reproduction: Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
🎯
Explore project logs, traces, and workspace in one view
Running
Reproduction: Theoretical Investigation on Inductive Bias of Isolation Forest
🎯
Explore and manage experiment logs, traces, and workspace online
Running
Reproduction: Context-free Recognition with Transformers
🎯
Explore and manage experiment logs with AI collaboration
Running
Reproduction: A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
🎯
Browse project logs, code, and traces in an interactive web logbook
Running
Reproduction: Alignment between Brains and AI: Evidence for Convergent Evolution across Modalities, Scales and Training Trajectories
🎯
Explore and share AI experiment logs in a web dashboard
Running
Reproduction: Envy-Free Allocation of Indivisible Goods via Noisy Queries
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
🎯
View and organize code, traces, and workspace in a logbook
Running
Reproduction: Test-Time Training with KV Binding Is Secretly Linear Attention
🎯
Explore code logs, traces, and workspace in a web logbook
Running
Reproduction: (Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential Games
🎯
Explore project logs and traces in a web dashboard
Running
Reproduction: Probabilistic Bisection Algorithm Provably Achieves Exponential Convergence
🎯
Explore code, execution traces, and workspace in an interactive logbook
Running
Reproduction: Perceptrons and localization of attention's mean-field landscape
🎯
Explore experiment logs, traces, and workspace online
Running
Reproduction: ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
🎯
Explore experiment logs, traces, and workspace in a web UI
Running
Reproduction: Towards Understanding Adam Convergence on Highly Degenerate Polynomials
🎯
Explore and collaborate on project logs, traces, and workspace
Running
Reproduction: Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective
🎯
Explore code, traces, and workspace in an interactive logbook