56 citations · 121 across the 49 of their papers we have counts for
25 papers · 1 filter
From Tokens to Trajectories: Parameter-Efficient Continuous Adaptation of Unified Multimodal Models
Gayatri Deshmukh, Onkar Susladkar, Adheesh Juvekar +2
While discrete tokenization in Unified Multimodal Models (UMMs) establishes strong semantic reasoning, it introduces a strict quantization bottleneck that degrades fine-grained vis…
CoDA: Co-Evolution of Data Engines and Action Policies
Tianjiao Yu, Zhilin Ou, Yifan Shen +5
Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environme…
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation
Tianjiao Yu, Xinzhuo Li, Yifan Shen +4
High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective…
LIBERO-MAX: Do Robot Policies Adapt When the World Changes?
Yunbei Zhang, Zijian Jin, Yuanzhe Liu +14
Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previ…
DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation
Haoran Yuan, Zekai Wang, Boning Shao +4
Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple predictive video world modeling wi…
One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
Adheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen +6
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We in…
GraphVid: Interactive Graph-Controllable Video Generation
Vedant Shah, Onkar Susladkar, Tushar Prakash +5
Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily c…
Decoding Children's Gait Behavior
Yifan Shen, Boyi Li, Meihuan Huang +12
We introduce a new problem domain for human action recognition: the fine-grained analysis of children's gait behaviors from standard RGB video. We specifically target the ambulator…
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
Tianjiao Yu, Xinzhuo Li, Yifan Shen +4
Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit. Existi…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Yanjun Zhao, Ruizhong Qiu, Tianxin Wei +6
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support incre…
CogniRoute: Learning to Route Social Evidence in Omni-Modal Models
Yifan Shen, Pei Tian, Xinzhuo Li +8
Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially prono…
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
Xiaona Zhou, Muntasir Wahed, Tianjiao Yu +2
Recent advances in Vision--Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large la…
Evaluating Cognitive Age Alignment in Interactive AI Agents
Yifan Shen, Jiawen Zhang, Jian Xu +4
While agentic AI and its core multimodal large language models (MLLMs) have demonstrated remarkable promise in language and visual reasoning across domains ranging from daily life…
Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics
Ying Shen, Jerry Xiong, Tianjiao Yu +1
Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However, emerging evidence suggests…
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
Makanjuola Ogunleye, Eman Abdelrahman, Ismini Lourentzou
Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe…
RewardFlow: Generate Images by Optimizing What You Reward
Onkar Susladkar, Dong-Hwan Jang, Tushar Prakash +7
We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow…
VTAM: Efficient Visuo-Tactile World-Action Models for Contact-Rich Manipulation without Tactile Pretraining
Haoran Yuan, Weigang Yi, Zhenyu Zhang +11
Tactile vision-language-action models (VLAs) and tactile world-action models (WAMs) are a promising new paradigm for contact-rich manipulation, but existing models either underutil…
EgoForge: Goal-Directed Egocentric World Simulator
Yifan Shen, Jiateng Liu, Xinzhuo Li +9
Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object intera…
DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising
Tianjiao Yu, Xinzhuo Li, Muntasir Wahed +4
Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic…
GazeXPErT: An Expert Eye-tracking Dataset for Interpretable and Explainable AI in Oncologic FDG-PET/CT Scans
Joy T Wu, Daniel Beckmann, Sarah Miller +15
[18F]FDG-PET/CT is a cornerstone imaging modality for guiding oncology therapies, yet human expert shortages necessitate more efficient diagnostic aids. While standalone AI models…
FASA: Frequency-aware Sparse Attention
Yifei Wang, Yueqi Wang, Zhenrui Yue +6
The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address th…
PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
Onkar Susladkar, Tushar Prakash, Adheesh Juvekar +4
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 limite…
Toward Cognitive Supersensing in Multimodal Large Language Model
Boyi Li, Yifan Shen, Yuanzhe Liu +12
Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited…
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
Onkar Susladkar, Tushar Prakash, Gayatri Deshmukh +8
We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific l…