conftrace_
← Authors

Song Guo

47 papers · 2021–2026 · 10 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🧭 Keyword Pioneer 🌍 Conference Polyglot (9) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (12) 🐝 Cross-Pollinator (5)
🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🐣 Hot Topic Early Bird πŸ† Grand Slam πŸ‘‘ Triple Crown 🀝 Dynamic Duo (15) πŸ”₯ Unstoppable (5) πŸ’Ž Century Club (44) πŸ—ƒοΈ Keyword Collector (168) ⚑ Prolific Year (11)

Conferences

AAAI (9) CVPR (9) ICML (6) NIPS (6) ICCV (4) ICLR (4) IJCAI (4) ACL (2) ECCV (2) EMNLP (1)

Top co-authors

Jie Zhang (17) Jingcai Guo (15) Wenchao Xu (10) Ziming Liu (9) Xiaocheng Lu (8) Qihua ZHOU (7) Xiaosong Ma (7) Ruibin Li (6) Haozhao Wang (5) Xueyang Tang (5)

Keywords

federated learning (9) diffusion model (5) zero-shot learning (5) model compression (3) transfer learning (3) model aggregation (3) visual-semantic mapping (3) vision-language model (3) compositional zero-shot learning (3) representation learning (3) contrastive learning (2) privacy attack (2) domain generalization (2) communication efficiency (2) test-time adaptation (2) distributed learning (2) multi-modal learning (2) multi-label learning (2) knowledge distillation (2) semi-supervised learning (2)

Papers

LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning ACL 2026 Predicting the Future by Retrieving the Past AAAI 2026 Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models ACL 2026 RORem: Training a Robust Object Remover with Human-in-the-Loop CVPR 2025 Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition CVPR 2025 FreeMesh: Boosting Mesh Generation with Coordinates Merging ICML 2025 Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View ICLR 2025 HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models EMNLP 2025 DeNC: Unleash Neural Codecs in Video Streaming with Diffusion Enhancement AAAI 2025 Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning AAAI 2025 MjΓΆlnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion AAAI 2025 Durable Quantization Conditioned Misalignment Attack on Large Language Models ICLR 2025 Causally Motivated Sycophancy Mitigation for Large Language Models ICLR 2025 Enhancing Transferability of Targeted Adversarial Examples via Inverse Target Gradient Competition and Spatial Distance Stretching ICCV 2025 IRASim: A Fine-Grained World Model for Robot Manipulation ICCV 2025 InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis ICCV 2025 TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning IJCAI 2025 Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization ICML 2024 Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing NIPS 2024 Cross-modal Representation Flattening for Multi-modal Domain Generalization NIPS 2024 ProCC: Progressive Cross-Primitive Compatibility for Open-World Compositional Zero-Shot Learning AAAI 2024 On the Robustness of Neural-Enhanced Video Streaming against Adversarial Attacks AAAI 2024 DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning CVPR 2024 C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation CVPR 2024 Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models ECCV 2024 Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection ECCV 2024 Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients ICLR 2024 Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring ICML 2024 Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models ICML 2024 ParsNets: A Parsimonious Composition of Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning IJCAI 2024 (ML)$^2$P-Encoder: On Exploration of Channel-Class Correlation for Multi-Label Zero-Shot Learning CVPR 2023 Towards Test-Time Refusals via Concept Negation NIPS 2023 Graph Knows Unknowns: Reformulate Zero-Shot Learning as Sample-Level Graph Recognition AAAI 2023 Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle ICCV 2023 Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning CVPR 2023 PMR: Prototypical Modal Rebalance for Multimodal Learning CVPR 2023 PASS: Patch Automatic Skip Scheme for Efficient Real-Time Video Perception on Edge Devices AAAI 2023 MGIA: Mutual Gradient Inversion Attack in Multi-Modal Federated Learning (Student Abstract) AAAI 2023 Anchor Sampling for Federated Learning with Partial Client Participation ICML 2023 Towards Unbiased Training in Federated Open-world Semi-supervised Learning ICML 2023 SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models NIPS 2023 Layer-Wised Model Aggregation for Personalized Federated Learning CVPR 2022 Personalized Federated Learning with Contextualized Generalization IJCAI 2022 A Survey on Gradient Inversion: Attacks, Defenses and Future Directions IJCAI 2022 Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning NIPS 2022 Online Multiple Object Tracking With Cross-Task Synergy CVPR 2021 Parameterized Knowledge Transfer for Personalized Federated Learning NIPS 2021