JB
Jinhe Bi
cs.AIcs.CLcs.CVcs.LGcs.MA
On Valency
published · living versionsW_w6dz5kha·v1 · currentpublished
GradCO: Behavior-Aware Gradient-Conflict Offloading for Text-Based Person Anomaly Search
with Zhiheng Fu, Zixu Li, Zhiwei Chen, Jiale Huang +2
1 version
W_asrgyevp·v1published
W_3rh7ab5n·v1published
Preprints & journals
21 papers in the corpus · 2023–2026MAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy2608.16697v2 · Aniri, Chen Yilin, Jinhe Bi et al.2026 · 0 citationsarXiv
MemWM: Memory-Augmented Text-Based World Model2608.07107v2 · Yujun Wang, Tao Zhang, Jinhe Bi et al.2026 · 0 citationsarXiv
OPD-V: Visual On-Policy Self-Distillation with Modality Balance2608.05131v2 · Aniri, Jinhe Bi, Peng Liao et al.2026 · 0 citationsarXiv
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation2608.03791v1 · Chunlin Liu, Junnian Chen, Haitong Jiang et al.2026 · 0 citationsarXiv
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning2608.03972v1 · Jinhe Bi, Chennan Zhou, Zengjie Jin et al.2026 · 0 citationsarXiv
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution2607.05297v1 · Zefeng Wang, Minxi Yan, Jinhe Bi et al.2026 · 0 citationsarXiv
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence2606.15932v3 · Xuanle Zhao, Qiushi Sun, Jingyu Xiao et al.2026 · 0 citationsarXiv
DeepLook: Uncertainty-Guided Branching with Lookahead Confidence for Efficient Reasoning2607.22602v2 · Tingxin Yang, Zefeng Wang, Mengyue Wang et al.2026 · 0 citationsarXiv
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing2606.01393v1 · Minglai Yang, Xinyan Velocity Yu, Pengyuan Li et al.2026 · 0 citationsarXiv
EchoRL: Reinforcement Learning via Rollout Echoing2605.31228v1 · Jinhe Bi, Aniri, Minglai Yang et al.2026 · 0 citationsarXiv
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning2605.17065v1 · Sikuan Yan, Sicheng Dong, Haotong Wang et al.2026 · 0 citationsarXiv
Graph is a Substrate Across Data Modalities2601.22384v2 · Ziming Li, Xiaoming Wu, Zehong Wang et al.2026 · 0 citationsarXiv
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models2511.02650v2 · Tianfan Peng, Yuntao Du, Pengzhou Ji et al.2025 · 0 citationsarXiv
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls2510.19316v2 · Kailin Jiang, Hongbo Jiang, Ning Jiang et al.2025 · 0 citationsarXiv
Reinforcement Mid-Training2509.24375v1 · Yijun Tian, Shaoyu Chen, Zhichao Xu et al.2025 · 0 citationsarXiv
Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE2509.24130v3 · Guancheng Wan, Lucheng Fu, Haoxin Liu et al.2025 · 0 citationsarXiv
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM2506.14766v3 · Yujun Wang, Aniri, Jinhe Bi et al.2025 · 4 citationsProceedings of the AAAI Conference on Artificial Intelligence, 40(12): 10306-10314, 2026
Self-Evolving Multi-Agent Systems via Textual Backpropagation2506.09046v3 · Xiaowen Ma, Yunpu Ma, Chenyang Lin et al.2025 · 2 citationsarXiv
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection2502.12119v5 · Jinhe Bi, Aniri, Zengjie Jin et al.2025 · 0 citationsarXiv
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering2412.12359v2 · Jinhe Bi, Yujun Wang, Haokun Chen et al.2024 · 11 citationsarXiv
SPOT! Revisiting Video-Language Models for Event Understanding2311.12919v2 · Gengyuan Zhang, Jinhe Bi, Jindong Gu et al.2023 · 0 citationsarXiv
Career total: 25 works. 21 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.