Daily report — 2026-10-09
162 new papers screened · 10 analyzed · 0 reproduction runs · markdown
Reproductions
| status | paper | backend | claims matched |
|---|---|---|---|
| No reproduction runs today (opt-in). | |||
Top candidates
| score | paper | feasibility |
|---|---|---|
| 71.1 | Transformed Samplers with Variance Reduction Markov chain Monte Carlo (MCMC) methods are the standard tool for computing expectations under complex probability distributions. Control variates reduce the variance of the resulting estimates, but a good control variate requires solving the Poisson equation of the sampler, which rarely admits a closed-form solution. Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + concrete method ("closed-form"); + formal statement ("Theorem"); + claims simplicity ("simple"); no public code found; + keywords: sampling, kernel, monte carlo | 8/10 heuristic |
| 67.1 | Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of key-value representations for every data point during training, and retrieves and recombines these representations through an attention mechanism at inference time - resulting in a growing neural net (NN). While Irie et al. Claimed: none extracted Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + formal statement ("theorem"); + claims simplicity ("simple"); - survey/position (no method) ("perspective"); + code: https://github.com/paradigms-of-intelligence/rcdl; + keywords: optimizer, retrieval, kernel; + 6 HF upvotes | 6/10 heuristic |
| 64.7 | RIFT: Relative Isolation From Trees For Anomaly Detection Isolation Forest (IF) is a widely used baseline for unsupervised anomaly detection. Recent studies provide a closed-form expression for the infinite-forest limit for one-dimensional data. Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmark"); + explicit algorithm/pseudocode ("Algorithm 1"); + concrete method ("closed-form"); + formal statement ("Theorem"); + claims simplicity ("simple"); no public code found | 9/10 heuristic |
| 61.1 | Training on the Future: A Delay-Aware Audit of Test-Time Adaptation for Time-Series Forecasting Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth. But the label of an $H$-step forecast exists only $H$ steps later, and real data pipelines add further delay. Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + public benchmarks ("benchmarks"); + concrete method ("closed-form"); + formal statement ("bound"); + claims simplicity ("simple"); + code: https://github.com/Xodios/TRAINING-ON-THE-FUTURE-A-DELAY-AWARE-AUDIT-OF-TEST-TIME-ADAPTATION-FOR-TIME-SERIES-FORECASTING | 7/10 heuristic |
| 58.9 | Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-guided generation (IEG), where transformations can preserve visual identity while breaking physical continuity. Claimed: none extracted Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmarks"); - system/framework (many moving parts) ("framework"); + code: https://github.com/luping-liu/FreeMatching; + 28 HF upvotes | 6/10 heuristic |
| 58.4 | ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning Reinforcement learning from verifiable rewards (RLVR) frequently reuses rollouts across multiple policy updates, increasing the mismatch between the current policy and the data-generating policy. We identify a sign-dependent gradient starvation problem in clipped policy optimization: clipping suppresses under-generated positive responses at the low-importance-weight tail while permitting severely Claimed: none extracted Evidence: + public benchmarks ("benchmark"); + formal statement ("bound"); + code: https://github.com/yhangchen/ReSPO-code; + keywords: kernel, variational; + 7 HF upvotes | 5/10 heuristic |
| 54.7 | Prediction-Powered Data Fusion for Treatment Effect Estimation Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observational studies (OBS) are large but may be confounded. Many estimators combining a small RCT with a large OBS have been developed for the average treatment effect (ATE) and the conditional ATE (CATE). Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + concrete method ("closed-form"); + formal statement ("bound"); - system/framework (many moving parts) ("framework"); + code: https://github.com/CausalDataScience/DataFusionPPI | 6/10 heuristic |
| 54.7 | From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce. We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation. Claimed: none extracted Evidence: - LLM-based ("LLM"); + toy/synthetic experiments ("Simulation"); + small/synthetic data ("simulated"); + claims simplicity ("simple"); - system/framework (many moving parts) ("Agentic"); + code: https://github.com/ruyue0001/trace2env; + 164 HF upvotes | 6/10 heuristic |
| 53.6 | A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to approach BBO by combining task semantics, computation, optimization tools, and feedback-driven decision making, showing great potential due to the integration with mathematically rigorous tools. Claimed: none extracted Evidence: - LLM-based ("LLM"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmark"); - system/framework (many moving parts) ("Agentic"); + code: https://github.com/lamda-bbo/agentic-bbo; + keywords: optimizer; + 2 HF upvotes | 5/10 heuristic |
| 52.1 | LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression Deep randomized models fix hidden-layer parameters through random initialization and learn only closed-form readouts, typically adding depth by stacking random trans formations without target-aware control of hidden-state evolution. We propose LAIR Net, the Leaky Alignment-Impulse Residual Network, which mixes a shallow learned anchor into each hidden state through a leaky residual transition. Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + toy/synthetic experiments ("simulations"); + public benchmarks ("benchmark"); + concrete method ("closed-form"); + formal statement ("bound"); no public code found | 7/10 heuristic |