47 citations · 100 across the 16 of their papers we have counts for
18 papers
Embodied Playground: A Long-Horizon Agentic Robotics Benchmark for Physical, Strategic, and Spatial Reasoning
Feng Chen, Pei Zhou, Lixuan He +7
Foundation models offer a promising basis for robotic agents, but long-horizon tasks require them to sustain coherent reasoning and reliable physical execution across interdependen…
From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao, Jiahao Wang, Penghao Wu +18
Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragmen…
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
Zhiwei Ning, Wenwen Tong, Xiangli Kong +12
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-cent…
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Haiwen Diao, Penghao Wu, Hanming Deng +55
Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fra…
V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
Zhiwei Ning, Xuanang Gao, Jiaxi Cao +6
Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although re…
Kirchhoff index of a nested geometric graph with weighted multiple edges
Da-yeon Huh
Kirchhoff index, Kf(G), introduced by Klein and Randic in 1993, represents the total effective resistances between all pairs of vertices in a graph G, where each edge is regarded a…
SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
Yong Xien Chng, Tao Hu, Wenwen Tong +10
While Vision-Language Models (VLMs) can solve complex tasks through agentic reasoning, their capabilities remain largely constrained to text-oriented chain-of-thought or isolated t…
Scaling Spatial Intelligence with Multimodal Foundation Models
Zhongang Cai, Ruisi Wang, Chenyang Gu +26
Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation m…
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Changyao Tian, Hao Li, Gen Luo +11
Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs th…
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
Haiwen Diao, Mingxuan Li, Silei Wu +6
The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical modular VLMs, shaped by evolving model architectures and training paradigms. Yet, t…
Holistic Evaluation of Multimodal LLMs on Spatial Intelligence
Zhongang Cai, Yubo Wang, Qingping Sun +21
Multimodal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, the very cap…
DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
Erfei Cui, Wenhai Wang, Zhiqi Li +7
Large language models (LLMs) have opened up new possibilities for intelligent agents, endowing them with human-like thinking and cognitive abilities. In this work, we delve into th…
Scene as Occupancy
Chonghao Sima, Wenwen Tong, Tai Wang +8
Human driver can easily describe the complex traffic scene by visual system. Such an ability of precise perception is essential for driver's planning. To achieve this, a geometry-a…
3D Data Augmentation for Driving Scenes on Camera
Wenwen Tong, Jiangwei Xie, Tianyu Li +7
Driving scenes are extremely diverse and complicated that it is impossible to collect all cases with human effort alone. While data augmentation is an effective technique to enrich…
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Hongyang Li, Chonghao Sima, Jifeng Dai +19
Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches…
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang +6
Transformer, as a strong and flexible architecture for modelling long-range relations, has been widely explored in vision tasks. However, when used in video inpainting that require…
Decoupled Spatial-Temporal Transformer for Video Inpainting
Rui Liu, Hanming Deng, Yangyi Huang +6
Video inpainting aims to fill the given spatiotemporal holes with realistic appearance but is still a challenging task even with prosperous deep learning approaches. Recent works i…
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
Jingru Tan, Gang Zhang, Hanming Deng +4
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020. In this work, two characteristics of LVIS dataset are mainly considered: the long-tailed dis…