A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Seakr introduces self-aware knowledge retrieval to enable adaptive retrieval augmented generation, dynamically deciding when and what to retrieve.
Unknown
AdaptVision proposes adaptive visual acquisition to reduce visual tokens in vision-language models, improving efficiency for visual question answering.
Unknown
The paper proposes an adaptive reasoning framework that learns when to allocate additional test-time compute, reducing over-computation in RL-trained reasoning models.
Hongyu Chen, Liang Lin, Guangrun Wang
SVR uses joint verdict-confidence reinforcement learning to train models to self-verify answers, enabling adaptive test-time compute allocation.
Kaushalraj Puwar, B. Thangaraju
Adaptive Bridge is a proxy layer that decouples critical ROS 2 subscribers from degraded ones via topic splitting and dynamic rate control, cutting tail latency from 15 s to 1.55 ms.
Wenrui Bao, Zhiben Chen, Dan Xu, et al.
Learn2PD trains a lightweight filter to adaptively unmask tokens in diffusion LLMs, achieving up to 22.58x speedup without performance loss.
Qi Sun, Edoardo Cetin, Yujin Tang
Transformer-Squared is a self-adaptive LLM framework that adjusts only the singular components of weight matrices in real-time, using a two-pass dispatch and reinforcement-learned expert vectors to outperform LoRA with fewer parameters.
Frank L. Lewis, Draguna Vrabie, Kyriakos G. Vamvoudakis
This paper unifies adaptive and optimal control using reinforcement learning to design optimal adaptive controllers for discrete- and continuous-time systems without full dynamics knowledge.
Takyoung Kim, Kang-wook Kim, Sang Hoon Woo, et al.
DuplexGen generates scenario-adaptive turn-taking dialogues by calibrating LLM predictions with human preference annotations, outperforming uncalibrated prompting and generic human-human data.
Unknown
This paper introduces self-adaptive physics-informed neural networks that dynamically adjust loss weights during training to improve solution accuracy for nonlinear PDEs.
Aslı Durmuşoğlu, Şahin Yıldırım
This paper proposes a robust adaptive neuro-fuzzy inference system (RANFIS) for active landing-gear vibration control, achieving superior performance over MBNN and ANFIS in reducing vibration peaks, settling times, and steady-state errors.
Unknown
This paper introduces Markov games as a formal framework for multi-agent reinforcement learning, extending MDPs to settings with multiple adaptive agents.