18 papers
LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models
Zixuan Liu, Nan Xue, Rui Bao +4
Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. However, generating each token still involves sequential computation and repeat…
Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints
Haoxuan Gao, Qin-Wen Luo, Xiang Chen +5
External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make…
Human-Centric Intelligence in the Era of Foundation Models: A Survey
Yang Chen, Tianqi Wang, Xiaorui Jiang +13
Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated w…
WSA: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
Jiahao Jiang, Jianing Zhang, Zhenhan Yin +9
World-Action Models (WAMs) have emerged as a promising paradigm for robot control by using predicted world evolution to guide action generation. However, existing WAMs largely foll…
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
Chaofan Ma, Zhenjie Mao, Yuhuan Yang +5
Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory. Existing methods rely on single-turn inf…
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
Yujing Liu, Yixin Liu, Yu Zheng +3
Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining. Nevertheless, existing approaches primarily focus on aligning…
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
Fanqin Zeng, Feng Hong, Geng Yu +6
Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing mult…
Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer
Yue Niu, Zhaokai Sun, Jiayi Yang +5
Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, whi…
Towards One-for-All Anomaly Detection for Tabular Data
Shiyuan Li, Yixin Liu, Yu Zheng +3
Tabular anomaly detection (TAD) aims to identify samples that deviate from the majority in tabular data and is critical in many real-world applications. However, existing methods f…
PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learning
Jiaying Wu, Can Gao, Jinglu Hu +3
Few-shot learning aims to identify novel categories from only a handful of labeled samples, where prototypes estimated from scarce data are often biased and generalize poorly. Sema…
Preference-driven Knowledge Distillation for Few-shot Node Classification
Xing Wei, Chunchun Chen, Rui Fan +3
Graph neural networks (GNNs) can efficiently process text-attributed graphs (TAGs) due to their message-passing mechanisms, but their training heavily relies on the human-annotated…
Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
Xiaofeng Cao, Mingwei Xu, Xin Yu +8
Learning with high-resource data has demonstrated substantial success in artificial intelligence (AI); however, the costs associated with data annotation and model training remain…
Long-tailed Recognition with Model Rebalancing
Jiaan Luo, Feng Hong, Qiang Hu +3
Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally preve…
An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivity
Yuxiao Lee, Xiaofeng Cao, Wei Ye +3
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot out-of-distribution (OOD) detection capabilities, vital for reliable AI systems. Despite this pr…
TsCA: On the Semantic Consistency Alignment via Conditional Transport for Compositional Zero-Shot Learning
Miaoge Li, Jingcai Guo, Richard Yi Da Xu +4
Compositional Zero-Shot Learning (CZSL) aims to recognize novel state-object compositions by leveraging the shared knowledge of their primitive components. Despite considerable pro…
Concept Matching with Agent for Out-of-Distribution Detection
Yuxiao Lee, Xiaofeng Cao, Jingcai Guo +3
The remarkable achievements of Large Language Models (LLMs) have captivated the attention of both academia and industry, transcending their initial role in dialogue generation. To…
Dual Expert Distillation Network for Generalized Zero-Shot Learning
Zhijie Rao, Jingcai Guo, Xiaocheng Lu +5
Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping…
DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction
Cong Wang, Xiaofeng Cao, Lanzhe Guo2 +1
Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match mode…