Running Reproduction: Temporal Straightening for Latent Planning 🎯 Explore code logs, execution traces, and workspace in a web logbook
Running Reproduction: Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions 🎯 Explore code logs, traces, and workspace in a collaborative UI
Running Reproduction: Probabilistic Retrofitting of Learned Simulators 🎯 Explore code, traces, and workspace in an interactive logbook
Running Reproduction: 1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization 🎯 Explore research logs, code, and traces in a web dashboard
Running Reproduction: De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution 🎯 Explore agent logs, traces and collaborate via a web logbook
Running Reproduction: Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions 🎯 Browse and manage project logs, traces, and workspace
Running Reproduction: RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models 🎯 Explore and manage experiment logs with code, traces, and workspace
Running Reproduction: Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios 🎯 View project logs, traces, and workspace with AI assistance
Running Reproduction: On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning 🎯 Explore and collaborate on project logs and code online
Running Reproduction: On the Ability of Transformers to Verify Plans 🎯 Explore code logs, traces, and workspace in a collaborative UI
Running Reproduction: IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference 🎯 Explore and manage experiment logs, traces, and workspace
Running Reproduction: TriAttention: Efficient Long Reasoning with Trigonometric KV Compression 🎯 Explore code logs, traces, and workspace in a web UI
Running Reproduction: Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection 🎯 Explore experiment logs and collaborate with an AI agent
Running Reproduction: Multi-Round Human-AI Collaboration with User-Specified Requirements 🎯 Explore and share AI collaboration logs
Running Reproduction: Large-Scale Notification Dispatch with Bundle Treatments and Multi-Outcome Uplift Optimization 🎯 Explore notification experiment logs
Running Reproduction: Innovation: An Almost Characterization of Hallucination 🎯 Explore code, traces, and workspace in an interactive logbook
Running Reproduction: On the Robustness of Langevin Dynamics to Score Function Error 🎯 Explore experiment logs, traces and workspace online
Running Reproduction: Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design 🎯 Explore and manage experiment logs, traces, and workspace
Running Reproduction: ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering 🎯 Explore ML agent logs and traces in an interactive logbook
Running Reproduction: CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability 🎯 Collaborate with an AI agent to track code security findings
Running Reproduction: TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding 🎯 Explore research logbook and sync notes with an AI agent