Research radar

arXiv preprints, filtered for developer impact.

Concise summaries of new AI papers, ranked for how likely they are to change how production systems are built. arXiv collection remains rate-limited.

Papers tracked

3,367

matching records

Shown

current page

Top radar

http://arxiv.org/abs/2610.06822v1

Code links

on this page

Paper	Authors	arXiv ID	Categories	Published	Code	Radar	Summary
Private online learning and prediction for Littlestone classes	Amartya Sanyal	http://arxiv.org/abs/2610.06822v1	cs.LG, cs.CR	Oct 5, 2026	None	Score64	We study mistake bounds for differentially private online learning and online prediction unde...
Point2Part: Unified 3D Partitioning from Point Prompts	Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma	http://arxiv.org/abs/2609.38180v1	cs.CV	Sep 29, 2026	None	Score71	Existing 3D part decomposition methods do not necessarily partition the original shape into n...
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation	Rishabh Agrawal, Hejie Cui, Shasha Li	http://arxiv.org/abs/2609.38142v1	cs.AI, cs.CL	Sep 29, 2026	None	Score65	A small trainable advisor can steer a frozen language-model executor using natural-language a...
Achieving an $O(1/N)$ Optimality Gap in Average-Reward Weakly-Coupled MDPs	Yige Hong, Xiangcheng Zhang, Qiaomin Xie	http://arxiv.org/abs/2609.38132v1	cs.LG, math.OC	Sep 29, 2026	None	Score64	We study average-reward weakly-coupled Markov decision processes (WCMDPs), where a WCMDP cons...
X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets	Prithwish Dan, Chenyang Ma, Wei Zhan	http://arxiv.org/abs/2609.35715v1	cs.LG, cs.AI	Sep 28, 2026	None	Score72	Reinforcement learning (RL) in simulation can train dexterous manipulation policies without r...
Mind the RefGAP: Correcting Reference Attention in Diffusion-Based Visual Editing	Yanan Wang, Shengcai Liao, Guangyi Liu	http://arxiv.org/abs/2609.35708v1	cs.CV	Sep 28, 2026	None	Score69	Reference-guided diffusion editors struggle to faithfully reproduce user-provided references....
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation	Zihan Wang, Zhen Wu, Pieter Abbeel	http://arxiv.org/abs/2609.38172v1	cs.RO, cs.CV	Sep 29, 2026	None	Score68	Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imi...
PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams	Trong-Tung Nguyen, Anand Bhattad	http://arxiv.org/abs/2609.38153v1	cs.CV	Sep 29, 2026	None	Score71	We introduce PowerSim, a method to bring physically grounded, differentiable dynamics to Powe...
LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation	Shengxiang Ji, Boyang Wang, Haiyang Xu	http://arxiv.org/abs/2609.38146v1	cs.CV	Sep 29, 2026	None	Score71	We introduce LIFT, a unified image-to-video generation framework that complements camera cont...
Lagrangian--Hamiltonian Flows for Video Prediction and Image Generation: A Symplectic Perspective	Jiawei Hu	http://arxiv.org/abs/2609.35710v1	cs.CV	Sep 28, 2026	None	Score60	We introduce LHFM, a geometric framework for learning image dynamics. Drawing on structures c...