Tootfinder

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
FaQiang Qian, WeiKun Zhang, Ziliang Wang, Kang An, Xuhui Zheng, Liangjian Wen, Mengya Gao, Yong Dai, Yichao Wu
https://arxiv.org/abs/2509.25148

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
Shaping powerful LLMs to be beneficial and safe is central to AI alignment. We argue that post-training alignment is fundamentally a unified Preference Learning problem, involving two modalities: demonstrated preferences (e.g., Supervised Fine-Tuning, SFT) and comparative preferences (e.g., Reinforcement Learning, RL).The standard sequential pipeline-SFT followed by RL-is flawed due to a critical distributional mismatch: SFT uses static expert data, but as the policy evolves, its generation dis…

Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation
Erdun Gao, Jake Fawkes, Dino Sejdinovic
https://arxiv.org/abs/2509.21866 https://

Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation
Estimating the Conditional Average Treatment Effect (CATE) is often constrained by the high cost of obtaining outcome measurements, making active learning essential. However, conventional active learning strategies suffer from a fundamental objective mismatch. They are designed to reduce uncertainty in model parameters or in observable factual outcomes, failing to directly target the unobservable causal quantities that are the true objects of interest. To address this misalignment, we introduce…

Eliciting User Requirements for AI-Enhanced Learning Environments using a Participatory Approach
Bibeg Limbu, Irene-Angelica Chounta, Vilma Sukacke, Andromachi Filippidi, Chara Spyropoulou, Marianna Anagnostopoulou, Eleftheria Tsourlidaki, Nikos Karacapilidis
https://arxiv.org/abs/2507.21088

Eliciting User Requirements for AI-Enhanced Learning Environments using a Participatory Approach
This paper explores the needs \& expectations of educational stakeholders for AI (Artificial Intelligence)-enhanced learning environments. Data was collected following two-phased participatory workshops. The first workshop outlined stakeholders' profiles in terms of technical and pedagogical characteristics. The qualitative data collected was analysed using deductive thematic analysis with Activity Theory, explicating the user needs. The second workshop articulated expectations related to the i…

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
KaiWen Wei, Kejun He, Xiaomian Kang, Jie Zhang, Yuming Yang, Jiang Zhong, He Bai, Junnan Zhu
https://arxiv.org/abs/2509.23649

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constrained by the reliance on purely autoregressive training. This approach focuses solely on predicting the next item while ignoring the rich internal structure of a user's interaction history, thus failing to grasp the underlying intent. To address this limitation, we propose Masked History Learning (MHL), a novel traini…

DyMoDreamer: World Modeling with Dynamic Modulation
Boxuan Zhang, Runqing Wang, Wei Xiao, Weipu Zhang, Jian Sun, Gao Huang, Jie Chen, Gang Wang
https://arxiv.org/abs/2509.24804 …

DyMoDreamer: World Modeling with Dynamic Modulation
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building world models that simulate environmental dynamics and generate synthetic experience, improving sample efficiency. However, conventional world models process observations holistically, failing to decouple dynamic objects and temporal features from static backg…

Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement
Mattias Cross, Anton Ragni
https://arxiv.org/abs/2508.20584 https://arxiv…

Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancement
Current flow-based generative speech enhancement methods learn curved probability paths which model a mapping between clean and noisy speech. Despite impressive performance, the implications of curved probability paths are unknown. Methods such as Schrodinger bridges focus on curved paths, where time-dependent gradients and variance do not promote straight paths. Findings in machine learning research suggest that straight paths, such as conditional flow matching, are easier to train and offer b…

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
Asher J. Hancock, Xindi Wu, Lihan Zha, Olga Russakovsky, Anirudha Majumdar
https://arxiv.org/abs/2509.22195

Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce actions often diminishes the VLM's foundational reasoning and multimodal understanding, hindering generalization to novel scenarios, instruction following, and semantic understanding. We argue that this catastrophic forgetting is due to a distribution mismatch …

A Greedy PDE Router for Blending Neural Operators and Classical Methods
Sahana Rayan, Yash Patel, Ambuj Tewari
https://arxiv.org/abs/2509.24814 https://arx…

A Greedy PDE Router for Blending Neural Operators and Classical Methods
When solving PDEs, classical numerical solvers are often computationally expensive, while machine learning methods can suffer from spectral bias, failing to capture high-frequency components. Designing an optimal hybrid iterative solver--where, at each iteration, a solver is selected from an ensemble of solvers to leverage their complementary strengths--poses a challenging combinatorial problem. While the greedy selection strategy is desirable for its constant-factor approximation guarantee to …

MTRec: Learning to Align with User Preferences via Mental Reward Models
Mengchen Zhao, Yifan Gao, Yaqing Hou, Xiangyang Li, Pengjie Gu, Zhenhua Dong, Ruiming Tang, Yi Cai
https://arxiv.org/abs/2509.22807

MTRec: Learning to Align with User Preferences via Mental Reward Models
Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we pr…

StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Chenyu Zhou, Tianyi Xu, Jianghao Lin, Dongdong Ge
https://arxiv.org/abs/2509.22558

StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM training on OR problems, existing works generally face two key limitations. First, outcome reward suffers from the credit assignment problem, where correct final answers can reinforce flawed reasoning. Second, conventional discriminative process supervision is myopic, failing to evaluate the interdependent steps of OR mo…