English
Related papers

Related papers: GuidedSampling: Steering LLMs Towards Diverse Cand…

200 papers

Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Mingchuan Ma , Yuhao Zhou , Jindi Lv , Yuxin Tian , Dan Si , Shujian Li , Qing Ye , Jiancheng Lv

This paper improves the performance of RRT$^*$-like sampling-based path planners by combining admissible informed sampling and local sampling (i.e., sampling the neighborhood of the current solution). An adaptive strategy regulates the…

Robotics · Computer Science 2024-04-16 Marco Faroni , Nicola Pedrocchi , Manuel Beschi

The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Dongjun Kim , Yeongmin Kim , Se Jung Kwon , Wanmo Kang , Il-Chul Moon

Inference-time scaling through multiple sample generation in combination with Process- or Outcome-Reward Model (PRM or ORM) re-ranking has proven effective for text-based reasoning in large language models. This paper investigates whether…

Computation and Language · Computer Science 2025-10-20 Minghan Wang , Thuy-Trang Vu , Ehsan Shareghi , Gholamreza Haffari

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Machine Learning · Computer Science 2021-10-05 Elie Aljalbout , Maximilian Ulmer , Rudolph Triebel

Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse rewards makes this process highly sample-inefficient, as models must navigate vast search spaces…

Machine Learning · Computer Science 2026-05-11 Ilia Mahrooghi , Aryo Lotfi , Emmanuel Abbe

Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs can generate irrelevant information that harms retrieval…

Information Retrieval · Computer Science 2023-06-19 Iain Mackie , Ivan Sekulic , Shubham Chatterjee , Jeffrey Dalton , Fabio Crestani

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural…

Computation and Language · Computer Science 2019-09-19 Yixin Nie , Songhe Wang , Mohit Bansal

We study the process through which reasoning models trained with reinforcement learning on verifiable rewards (RLVR) can learn to solve new problems. We find that RLVR drives performance in two main ways: (1) by compressing pass@$k$ into…

Machine Learning · Computer Science 2025-06-23 Vaskar Nath , Elaine Lau , Anisha Gunjal , Manasi Sharma , Nikhil Baharte , Sean Hendryx

Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for large-scale or dynamic environments. Sample-based methods…

Artificial Intelligence · Computer Science 2025-09-22 Tamir Shazman , Idan Lev-Yehudi , Ron Benchetit , Vadim Indelman

Sampling-based motion planners rely on incremental densification to discover progressively shorter paths. After computing feasible path $\xi$ between start $x_s$ and goal $x_t$, the Informed Set (IS) prunes the configuration space…

Robotics · Computer Science 2021-04-13 Aditya Mandalika , Rosario Scalise , Brian Hou , Sanjiban Choudhury , Siddhartha S. Srinivasa

The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to improve the cost-performance tradeoff. Existing strategies…

Computation and Language · Computer Science 2025-05-23 Jasper Dekoninck , Maximilian Baader , Martin Vechev

Sequential recommendation (SR) tasks aim to predict users' next interaction by learning their behavior sequence and capturing the connection between users' past interactions and their changing preferences. Conventional SR models often focus…

Information Retrieval · Computer Science 2024-12-19 Haoyi Zhang , Guohao Sun , Jinhu Lu , Guanfeng Liu , Xiu Susie Fang

Standard autoregressive decoding in large language models (LLMs) is inherently short-sighted, often failing to find globally optimal reasoning paths due to its token-by-token generation process. While inference-time strategies like…

Machine Learning · Computer Science 2026-01-23 Huayu Li , ZhengXiao He , Siyuan Tian , Jinghao Wen , Ao Li

Generative Recommendation (GR) has recently transitioned from atomic item-indexing to Semantic ID (SID)-based frameworks to capture intrinsic item relationships and enhance generalization. However, the adoption of high-granularity SIDs…

Information Retrieval · Computer Science 2026-04-08 Tianyu Zhan , Kairui Fu , Chengfei Lv , Zheqi Lv , Shengyu Zhang

Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homogeneous solutions. In such environments, the lack of failure…

Machine Learning · Computer Science 2026-04-21 Zhenwen Liang , Yujun Zhou , Sidi Lu , Xiangliang Zhang , Haitao Mi , Dong Yu

With ever-increasing dataset sizes, subset selection techniques are becoming increasingly important for a plethora of tasks. It is often necessary to guide the subset selection to achieve certain desiderata, which includes focusing or…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Suraj Kothawade , Vishal Kaushal , Ganesh Ramakrishnan , Jeff Bilmes , Rishabh Iyer

The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models…

Computation and Language · Computer Science 2024-12-20 Yuan Xia , Jingbo Zhou , Zhenhui Shi , Jun Chen , Haifeng Huang

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

Machine Learning · Computer Science 2025-12-30 Lei Wang , Zikun Ye , Jinglong Zhao

Pushdown systems (PDSs) and recursive state machines (RSMs), which are linearly equivalent, are standard models for interprocedural analysis. Yet RSMs are more convenient as they (a) explicitly model function calls and returns, and (b)…

Programming Languages · Computer Science 2020-01-13 Krishnendu Chatterjee , Bernhard Kragl , Samarth Mishra , Andreas Pavlogiannis