Tootfinder

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Yubo Li, Weiyi Song
https://arxiv.org/abs/2509.12179 https://arxiv.org/pd…

Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation
Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA), where humans and AI mutually adapt. BiCA uses learnable protocols, representation mapping, and KL-budget constraints for controlled co-evolution. In collaborative navigation, BiCA achieved 85.5% success versus 70.3% baseline, with 230% better mutual adaptation an…

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu, Weijie Su, Hanming Deng, Jinguo Zhu, Jie Shao, Ziran Zhu, Yunpeng Liu, Lewei Lu, Wenhai Wang, Hongsheng Li, Jifeng Dai
https://arxiv.org/abs/2510.08565 …

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training. However, the multimodal scaling property of this paradigm remains difficult to explore due to the separated training. In this paper, we focus on the native training of MLLMs in an end-to-end manner and systematically study its design space and scaling property under a practica…

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
Bianca-Mihaela Ganescu, Suchir Salhan, Andrew Caines, Paula Buttery
https://arxiv.org/abs/2510.08470

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight decoder-based architecture with (1) token-wise dynamic gating for adaptive fusion of linguistic and visual cues, (2) feature modulation and channel attention to maximise the utility of limited visual information and (3) auxiliary contrastive objectives for visua…

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
Jungwoo Kim, Minsang Kim, Jaeheon Lee, Chanwoo Moon, Heejin Kim, Taeho Hwang, Woosuk Chung, Yeseong Kim, Sungjin Lee
https://arxiv.org/abs/2508.18736

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
Serving Large Language Models (LLMs) at scale requires meeting strict Service Level Objectives (SLOs) under severe computational and memory constraints. Nevertheless, traditional caching strategies fall short: exact-matching and prefix caches neglect query semantics, while state-of-the-art semantic caches remain confined to traditional intuitions, offering little conceptual departure. Building on this, we present SISO, a semantic caching system that redefines efficiency for LLM serving. SISO in…

Prediction-Powered Communication with Distortion Guarantees
Matteo Zecchin, Unnikrishnan Kunnath Ganesan, Giuseppe Durisi, Petar Popovski, Osvaldo Simeone
https://arxiv.org/abs/2509.24373

Prediction-Powered Communication with Distortion Guarantees
The development of 6G wireless systems is taking place alongside the development of increasingly intelligent wireless devices and network nodes. The changing technological landscape is motivating a rethinking of classical Shannon information theory that emphasizes semantic and task-oriented paradigms. In this paper, we study a prediction-powered communication setting, in which devices, equipped with artificial intelligence (AI)-based predictors, communicate under zero-delay constraints with str…