English
Related papers

Related papers: Test-time Diverse Reasoning by Riemannian Activati…

200 papers

Generative molecular design has moved from proof-of-concept to real-world applicability, as marked by the surge in very recent papers reporting experimental validation. Key challenges in explainability and sample efficiency present…

Biomolecules · Quantitative Biology 2024-03-05 Jeff Guo , Philippe Schwaller

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

We propose a new approach to solve optimal stopping problems via simulation. Working within the backward dynamic programming/Snell envelope framework, we augment the methodology of Longstaff-Schwartz that focuses on approximating the…

Computational Finance · Quantitative Finance 2015-09-04 Robert B. Gramacy , Mike Ludkovski

We present general results on D-optimal designs for estimating the mean response in repeated measures growth curve models with metric outcomes. For this situation, we derive a novel equivalence theorem for checking design optimality. The…

Statistics Theory · Mathematics 2023-01-23 Fritjof Freise , Heinz Holling , Rainer Schwabe

Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality. To…

Computation and Language · Computer Science 2024-05-27 Lei Lin , Jiayi Fu , Pengli Liu , Qingyang Li , Yan Gong , Junchen Wan , Fuzheng Zhang , Zhongyuan Wang , Di Zhang , Kun Gai

Inference-time steering enables pretrained diffusion/flow models to be adapted to new tasks without retraining. A widely used approach is the ratio-of-densities method, which defines a time-indexed target path by reweighting…

Artificial Intelligence · Computer Science 2025-12-12 Ziseok Lee , Minyeong Hwang , Sanghyun Jo , Wooyeol Lee , Jihyung Ko , Young Bin Park , Jae-Mun Choi , Eunho Yang , Kyungsu Kim

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Artificial Intelligence · Computer Science 2025-08-12 Annie Wong , Thomas Bäck , Aske Plaat , Niki van Stein , Anna V. Kononova

Large language models (LLMs) excel in natural language generation but often confidently produce incorrect responses, especially in tasks like mathematical reasoning. Chain-of-thought prompting, self-verification, and multi-agent debate are…

Computation and Language · Computer Science 2026-03-30 Mahmood Hegazy

We investigate the impact of Knightian uncertainty on the optimal timing policy of an ambiguity averse decision maker in the case where the underlying factor dynamics follow a multidimensional Brownian motion and the exercise payoff depends…

Probability · Mathematics 2019-07-10 Luis H. R. Alvarez E. , Sören Christensen

Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Qingyang Liu , Bingjie Gao , Canmiao Fu , Zhipeng Huang , Chen Li , Feng Wang , Shuochen Chang , Shaobo Wang , Yali Wang , Keming Ye , Jiangtong Li , Li Niu

Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on…

Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctness. Existing approaches either verify only the final answer, which misses early errors, or rely on…

We propose a variant of the Rapidly Exploring Random Tree Star (RRT$^{\star}$) algorithm to synthesize trajectories satisfying a given spatio-temporal specification expressed in a fragment of Signal Temporal Logic (STL) for linear systems.…

Systems and Control · Electrical Eng. & Systems 2025-06-13 Gregorio Marchesini , Siyuan Liu , Lars Lindemann , Dimos V. Dimarogonas

Current research in multimodal models faces a key challenge where enhancing generative capabilities often comes at the expense of understanding, and vice versa. We analyzed this trade-off and identify the primary cause might be the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Sen Ye , Mengde Xu , Shuyang Gu , Di He , Liwei Wang , Han Hu

Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhance it. Motivated by the observed relationship between solution accuracy and meaningful…

Machine Learning · Computer Science 2025-12-22 Tianchun Wang , Zichuan Liu , Yuanzhou Chen , Jonathan Light , Weiyang Liu , Haifeng Chen , Xiang Zhang , Wei Cheng

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…

Computation and Language · Computer Science 2025-12-02 Canhui Wu , Qiong Cao , Chang Li , Zhenfang Wang , Chao Xue , Yuwei Fan , Wei Xi , Xiaodong He

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Artificial Intelligence · Computer Science 2026-05-29 Yang Ouyang , Shuhang Lin , Jung-Eun Kim

Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention…

This paper presents a continuous-time optimal control framework for the generation of reference trajectories in driving scenarios with uncertainty. A previous work presented a discrete-time stochastic generator for autonomous vehicles;…

Optimization and Control · Mathematics 2026-03-17 Ange Valli , Shangyuan Zhang , Abdel Lisser