69 citations · 75 across the 17 of their papers we have counts for
18 papers
Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning
Haotian Lyu, Haoyu Wang, Ru Wang +4
Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions. However, misinterpreted visual evidence and sensitivity…
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL
Shu Tong Luo, Wenqin Liu, Rui Liu +2
When a user reveals task-critical information across several conversation turns, LLM accuracy drops by up to 65% despite full context availability. We show that this Lost in Conver…
Towards High-resolution and Disentangled Reference-based Sketch Colorization
Dingkun Yan, Xinrui Wang, Ru Wang +5
Sketch colorization is a critical task for automating and assisting in the creation of animations and digital illustrations. Previous research identified the primary difficulty as…
HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models
Xin Xie, Jiaxian Guo, Dong Gong
Diffusion model alignment aims to bridge the gap between generated outputs and human preferences by enhancing both semantic consistency with textual prompts and overall visual qual…
Learning Plug-and-play Memory for Guiding Video Diffusion Models
Selena Song, Ziming Xu, Zijun Zhang +4
Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical l…
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
Ru Wang, Wei Huang, Qi Cao +3
Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable…
AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Haoyu Zhang, Jiaxian Guo, Dong Yang +2
Large Audio Language Models (LALMs) exhibit strong capabilities in general audio understanding but remain static after deployment, limiting their adaptability to real-world data. S…
Enhancing Reference-based Sketch Colorization via Separating Reference Representations
Dingkun Yan, Xinrui Wang, Zhuoru Li +4
Reference-based sketch colorization methods have garnered significant attention for the potential application in animation and digital illustration production. However, most existi…
Spark Transformer: Reactivating Sparsity in FFN and Attention
Chong You, Kan Wu, Zhipeng Jia +16
The discovery of the lazy neuron phenomenon in trained Transformers, where the vast majority of neurons in their feed-forward networks (FFN) are inactive for each token, has spurre…
ColorizeDiffusion v2: Enhancing Reference-based Sketch Colorization Through Separating Utilities
Dingkun Yan, Xinrui Wang, Yusuke Iwasawa +3
Reference-based sketch colorization methods have garnered significant attention due to their potential applications in the animation production industry. However, most existing met…
Image Referenced Sketch Colorization Based on Animation Creation Workflow
Dingkun Yan, Xinrui Wang, Zhuoru Li +4
Sketch colorization plays an important role in animation and digital illustration production tasks. However, existing methods still meet problems in that text-guided methods fail t…
Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization
Ru Wang, Wei Huang, Selena Song +5
Generalization to novel compound tasks under distribution shift is important for deploying transformer-based language models (LMs). This work investigates Chain-of-Thought (CoT) re…
Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection
Bo Yang, Jiaxian Guo, Yusuke Iwasawa +1
Recent studies have increasingly demonstrated that large language models (LLMs) possess significant theory of mind (ToM) capabilities, showing the potential for simulating the trac…
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
Xiabin Zhou, Wenbin Wang, Minyan Zeng +5
Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization. Existing KV cache compression methods enforce a fixed pattern, neglecting task-s…
Real-World Robot Applications of Foundation Models: A Review
Kento Kawaharazuka, Tatsuya Matsushima, Andrew Gambardella +3
Recent developments in foundation models, like Large Language Models (LLMs) and Vision-Language Models (VLMs), trained on extensive data, facilitate flexible application across dif…
Realtime Data-Efficient Portrait Stylization Based On Geometric Alignment
Xinrui Wang, Zhuoru Li, Xiao Zhou +2
Portrait Stylization aims to imbue portrait photos with vivid artistic effects drawn from style examples. Despite the availability of enormous training datasets and large network w…
DNQ: Dynamic Network Quantization
Yuhui Xu, Shuai Zhang, Yingyong Qi +3
Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices. In this paper, we propose a Dynamic Network Quant…