20 results for “In-context learning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper studies how transformers exploit task-relevant structure in geometrically heterogeneous data and provides a new estimator and generalization bound for in-context learning.
The paper introduces BDH-CQ, a reasoning model that combines in-context learning and recurrent latent reasoning, achieving 29.5% pass@2 at a low cost on ARC-AGI-1, surpassing the previous cost-accurac…
This paper introduces a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference.
Siyin Wang, Junhao Shi, Senyu Fei, Zhaoyang Fu +3 more
This paper introduces In-Context World Modeling (ICWM), a framework that enables robots to adapt to novel system configurations without requiring parameter updates.
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 a novel two-stage framework to achieve robust, category-agnostic object localization in-context (ICL) by optimizing attention and minimizing localization error using reinforcement…
ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.
The paper proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…
The paper introduces Involuntary In-Context Learning (IICL), an effective few-shot pattern completion attack that can bypass safety alignments in large language models, achieving a 24.0% bypass rate a…
This paper demonstrates that retrieval-augmented in-context learning systems for document QA are vulnerable to membership inference attacks, proposing novel black-box methods that exploit query prefix…
Peiyang Xu, Bangzheng Li, Sijia Liu, Karthik R. Narasimhan +3 more
This paper proposes ContextRL, a context-aware reinforcement learning method that improves long-horizon reasoning and multimodal performance by encouraging fine-grained grounding.
The paper introduces IndicContextEval, a multilingual benchmark to evaluate the use of contextual signals in AudioLLMs.
Ziyang Zheng, Zeju Li, Xiangyu Wen, Jianyuan Zhong +4 more
The paper reframes context distillation as a latent memory management problem, proposing a modular framework using LoRA adapters and a Self-Gating mechanism for efficient, selective memory retrieval a…
The paper proposes a training method to improve speech recognition by using video metadata and LLM-generated explanations to perform contextual reasoning.
Liad Erez, Fan Chen, Alon Cohen, Tomer Koren +3 more
The paper analyzes the sample complexity of contextual bandits in the $s$-sparse setting, achieving optimal sample bounds for identifying an $\epsilon$-optimal policy.
The paper proposes a context-weighted sampler and scaled cross-entropy loss function for discrete generative modeling to improve generation quality and reduce generative perplexity.
Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang +2 more
The paper proposes Conditional Retrieval Alignment (CoRA), a gradient-free framework for task-conditioned retrieval using a frozen encoder and paired inputs and outputs.
Ran Piao, Tsai-Ning Wang, Martijn den Dekker, Linda Moonen +3 more
This paper proposes a framework for clinical audio diagnosis in low-resource settings using a multimodal language model.
The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…
Yunpeng Hong, Chenyang Bu, Di Wu, Yi He +1 more
This paper proposes PTFEA, a curriculum-learning-inspired framework that translates fine-tuning strategies into interpretable context engineering for Multimodal Entity Alignment (MMEA), demonstrating…