Paper Archive

Wenhang Ge, Guibao Shen, Jiawei Feng, Luozhou Wang, Hao Lu, Xingye Tian, Xin Tao, Ying-Cong Chen 1/22/2026 arxiv

Recent advances in camera-controlled video diffusion models have significantly improved video-camera alignment. However, the camera controllability still remains limited. In this work, we build upon Reward Feedback Learning and aim to further improve camera controllability. However, directly borrowi...

Siddhant Haldar, Lars Johannsmeier, Lerrel Pinto, Abhishek Gupta, Dieter Fox, Yashraj Narang, Ajay Mandlekar 1/22/2026 arxiv

Robot foundation models are beginning to deliver on the promise of generalist robotic agents, yet progress remains constrained by the scarcity of large-scale real-world manipulation datasets. Simulation and synthetic data generation offer a scalable alternative, but their usefulness is limited by th...

Geo Ahn, Inwoong Lee, Taeoh Kim, Minho Shim, Dongyoon Wee, Jinwoo Choi 1/22/2026 arxiv

We study Compositional Video Understanding (CVU), where models must recognize verbs and objects and compose them to generalize to unseen combinations. We find that existing Zero-Shot Compositional Action Recognition (ZS-CAR) models fail primarily due to an overlooked failure mode: object-driven verb...

Onkar Susladkar, Tushar Prakash, Adheesh Juvekar, Kiet A. Nguyen, Dong-Hwan Jang, Inderjit S Dhillon, Ismini Lourentzou 1/22/2026 arxiv

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supervision, leading to poor cross-modal alignment and zero-shot transfer. We introd...

Shengbang Tong, Boyang Zheng, Ziteng Wang, Bingda Tang, Nanye Ma, Ellis Brown, Jihan Yang, Rob Fergus, Yann LeCun, Saining Xie 1/22/2026 arxiv

Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation. We first scale RAE decode...

Jongwoo Park, Kanchana Ranasinghe, Jinhyeok Jang, Cristina Mata, Yoo Sung Jang, Michael S Ryoo 1/22/2026 arxiv

Many Vision-Language-Action (VLA) models flatten image patches into a 1D token sequence, weakening the 2D spatial cues needed for precise manipulation. We introduce IVRA, a lightweight, training-free method that improves spatial understanding by exploiting affinity hints already available in the mod...

Daixuan Cheng, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen, Furu Wei 1/22/2026 arxiv

We introduce LLM-in-Sandbox, enabling LLMs to explore within a code sandbox (i.e., a virtual computer), to elicit general intelligence in non-code domains. We first demonstrate that strong LLMs, without additional training, exhibit generalization capabilities to leverage the code sandbox for non-cod...

Patrick Altmeyer, Aleksander Buszydlik, Arie van Deursen, Cynthia C. S. Liem 1/22/2026 arxiv

We propose a novel training regime termed counterfactual training that leverages counterfactual explanations to increase the explanatory capacity of models. Counterfactual explanations have emerged as a popular post-hoc explanation method for opaque machine learning models: they inform how factual i...

Song Xia, Meiwen Ding, Chenqi Kong, Wenhan Yang, Xudong Jiang 1/22/2026 arxiv

Multimodal large language models (MLLMs) exhibit strong capabilities across diverse applications, yet remain vulnerable to adversarial perturbations that distort their feature representations and induce erroneous predictions. To address this vulnerability, we propose the Feature-space Smoothing (FS)...

El Mehdi Er Raqabi, Kevin Dalmeijer, Pascal Van Hentenryck 1/22/2026 arxiv

This paper investigates the multi-compartment vehicle routing problem with multiple time windows (MCVRPMTW), an extension of the classical vehicle routing problem with time windows that considers vehicles equipped with multiple compartments and customers requiring service across several delivery tim...