20 results for “Reference-Augmented Training”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper proposes a Reference-Augmented Training (RAT) strategy to improve deepfake detection performance.
Zilin Xiao, Qi Ma, Chun-cheng Jason Chen, Xintao Chen +3 more
This paper proposes a post-training framework called Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT) to teach language models to reason by analogy.
Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei +6 more
This paper introduces RefCraft, a benchmark for evaluating AI agents' ability to incorporate visual references into webpage development.
Jingjie Lin, Bingbing Wang, Zihan Wang, Zhengda Jin +3 more
The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…
Wenhan Xiao, Ziwei Zhang, Chuanyue Yu, Xingcheng Fu +3 more
CRITIC-R1 introduces a structured critic framework that treats RAG critique as an explicit error diagnosis problem using reinforcement learning, significantly improving answer quality over strong RAG…
This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.
Xiaoyang Jiang, Yanlai Yang, Kenneth A. Norman, Brenden Lake +1 more
The paper introduces BabyCL, a continual multimodal learning framework that processes egocentric video data in a single chronological pass, demonstrating that meaningful word-referent mappings can be…
The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.
The paper introduces and evaluates five parameter alignment strategies that significantly mitigate catastrophic forgetting when continually pretraining multilingual expert language models across multi…
The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…
Zheng Yuan, Chuang Zhou, Linhao Luo, Siyu An +3 more
MoG proposes a novel Mixture of Experts framework for graph-based RAG, which uses hub graphs to guide the sparse activation of domain-specific expert graphs, significantly improving retrieval accuracy…
Bingyu Li, Da Zhang, Tao Huo, Zhiyuan Zhao +2 more
The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…
The paper proposes a training method to improve speech recognition by using video metadata and LLM-generated explanations to perform contextual reasoning.
The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…
The authors present a method called Sparse Context to improve the efficiency of reference-based diffusion models by reducing the number of reference tokens used in image generation.
The paper proposes an extended version of Hypencoder, a retrieval approach that encodes queries as shallow neural networks, achieving comparable effectiveness with fewer active parameters and higher s…