43 citations · 108 across the 70 of their papers we have counts for
77 papers
Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing
Haotian Zhang, Shucun Wang, Jinze Wu +6
Knowledge Tracing (KT) aims to assess students' dynamic knowledge states from their learning histories. While most existing KT methods focus on single-domain learning with notable…
Branch2Skill: Efficient Skill Evolution Through Reasoning Trees
Yanwei Ren, Haotian Zhang, Likang Xiao +5
Skill evolution improves agent skills through feedback over time, with failed trajectories often providing informative signals by revealing incomplete or misleading behaviors. Howe…
Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale
Yanhua Cheng, Bo Wang, Haotian Zhang +17
Traditional short-video recommendation systems match user interest to a fixed pool of pre-produced videos, which limits their ability to capture fine-grained and dynamic preference…
MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction
Peize Li, Fanhu Zeng, Tongda Xu +5
In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
MMAE: A Massive Multitask Audio Editing Benchmark
Ziyang Ma, Ruiqi Yan, Ruiyang Xu +35
We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.…
GRAIL: Generating Humanoid Loco-Manipulation from World Models
Tianyi Xie, Haotian Zhang, Jinhyung Park +17
Scaling humanoid loco-manipulation requires robot-compatible demonstrations across diverse objects, whole-body motions, and scene geometries, but teleoperation and motion capture a…
Attention Sinks and Outliers in Attention Residuals
Haozheng Luo, Haoran Dai, Shaoyang Zhang +10
We propose OASIS, an outlier- and sink-aware method that stabilizes dual-normalized attention-residual architectures through explicit null routing and token-to-depth null coupling.…
SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
Haotian Zhang, Xu Mo, Yixin Yu +7
Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short vid…
Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
Tianshi Cao, Jiawei Ren, Yuxuan Zhang +12
Closed-loop simulation is a core component of autonomous vehicle (AV) development, enabling scalable testing, training, and safety validation before real-world deployment. Neural s…
AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control
Xiangyi Wei, Fei Wang, Haotian Zhang +6
Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platform…
Decoupling Numerical and Structural Parameters: An Empirical Study on Adaptive Genetic Algorithms via Deep Reinforcement Learning for the Large-Scale TSP
Hongyu Wang, Yuhan Jing, Yibing Shi +3
Proper parameter configuration is a prerequisite for the success of Evolutionary Algorithms (EAs). While various adaptive strategies have been proposed, it remains an open question…
Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning
Yinan Xia, Haotian Zhang, Huiming Wang
Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking, often generating excessively long and redundant an…
Kimodo: Scaling Controllable Human Motion Generation
Davis Rempe, Mathis Petrovich, Ye Yuan +21
High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data sourc…
When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models
Qitong Wang, Haoran Dai, Haotian Zhang +2
While diffusion models have revolutionized visual content generation, their rapid adoption has underscored the critical need to investigate vulnerabilities, e.g., to backdoor attac…
Believe Your Model: Distribution-Guided Confidence Calibration
Xizhong Yang, Haotian Zhang, Huiming Wang +1
Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple cand…
Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression
Haotian Zhang, Feiyue Long, Yixin Yu +7
Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of M…
Efficient RLVR Training via Weighted Mutual Information Data Selection
Xinyu Zhou, Boyu Zhu, Haotian Zhang +2
Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are s…
VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
Joan Rodriguez, Haotian Zhang, Abhay Puri +14
We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding.…
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Shuochen Liu, Junyi Zhu, Long Shu +11
Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. Existing evaluations of this capability typically interle…
Making Reconstruction FID Predictive of Diffusion Generation FID
Tongda Xu, Mingwei He, Shady Abu-Hussein +6
It is well known that the reconstruction FID (rFID) of a VAE is poorly correlated with the generation FID (gFID) of a latent diffusion model. We propose interpolated FID (iFID), a…
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance
Yanwei Ren, Haotian Zhang, Likang Xiao +6
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reasoning Models. However, standa…
WildSVG: Towards Reliable SVG Generation Under Real-Word Conditions
Marco Terral, Haotian Zhang, Tianyang Zhang +8
We introduce the task of SVG extraction, which consists in translating specific visual inputs from an image into scalable vector graphics. Existing multimodal models achieve strong…
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Xiao Zhu, Xinyu Zhou, Boyu Zhu +5
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scala…