Papers Value prediction
“Value prediction” 태그가 달린 논문 115편 · 필터 해제
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
Digital learning systems consume concrete pseudorandom values rather than abstract random variables. These values enter the realized loss and its gradient during training. If a pseudorandom stream contains structure that…
Value predictionAuto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models
Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically acros…
Value predictionNASDAQ: Normalized Observation Space Dynamics-Augmented Q-Learning
Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and performance, with minor modifications a…
Reinforcement LearningValue predictionHow Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models, latent imagination models, future-video predictors, interactive neural…
Instruction FollowingValue predictionFlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet…
Value predictionQ-Delta: Beyond Key-Value Associative State Evolution
Linear attention reformulates sequence modeling as recurrent state evolution, enabling efficient linear-time inference. Under the key-value associative paradigm, existing approaches restrict the role of the query to the …
Value predictionRelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases
Relational databases (RDBs) remain the cornerstone of modern data systems and support diverse predictive tasks. Recent relational deep learning (RDL) methods enable end-to-end prediction by converting RDBs into graphs, w…
Self-Supervised LearningRepresentation LearningValue predictionTowards Sustainable Growth: A Multi-Value-Aware Retrieval Framework for E-Commerce Search
New item growth is critical for maintaining a healthy ecosystem in large-scale e-commerce platforms. However, existing systems tend to prioritize presenting users with already popular items, a phenomenon often referred t…
Value predictionTabPFN-3: Technical Report
Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this …
Value predictionPAWN: Piece Value Analysis with Neural Networks
Predicting the relative value of any given chess piece in a position remains an open challenge, as a piece's contribution depends on its spatial relationships with every other piece on the board. We demonstrate that inco…
Value predictionBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning
Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned…
Reinforcement LearningValue predictionPRAGMA: Revolut Foundation Model
Modern financial systems generate vast quantities of transactional and event-level data that encode rich economic signals. This paper presents PRAGMA, a family of foundation models for banking event sequences. Our approa…
Value predictionFraud DetectionLiftFormer: Lifting and Frame Theory Based Monocular Depth Estimation Using Depth and Edge Oriented Subspace Representation
Monocular depth estimation (MDE) has attracted increasing interest in the past few years, owing to its important role in 3D vision. MDE is the estimation of a depth map from a monocular image/video to represent the 3D st…
Monocular Depth EstimationValue predictionDPD-Cancer: Explainable Graph-Based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule anti-cancer activity across the NCI-60 panel, tr…
Activity PredictionValue predictionOn the Learnability of Offline Model-Based Optimization: A Ranking Perspective
Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assu…
Value predictionWhat Does Flow Matching Bring To TD Learning?
Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains unclear why or how this approach differs from standard critics. Contrary to conv…
Reinforcement LearningValue predictionSequential Regression for Continuous Value Prediction using Residual Quantization
Continuous value prediction plays a crucial role in industrial-scale recommendation systems, including tasks such as predicting users' watch-time and estimating the gross merchandise value (GMV) in e-commerce transaction…
Representation LearningRecommendation SystemsValue predictionAgentLTV: An Agent-Based Unified Search-and-Evolution Framework for Automated Lifetime Value Prediction
Lifetime Value (LTV) prediction is critical in advertising, recommender systems, and e-commerce. In practice, LTV data patterns vary across decision scenarios. As a result, practitioners often build complex, scenario-spe…
Value predictionEIDOS: Latent-Space Predictive Learning for Time Series Foundation Models
Most time series foundation models are pretrained by directly predicting future observations, which often yields weakly structured latent representations that capture surface noise rather than coherent and predictable te…
Value predictionMeta-Cognitive Reinforcement Learning with Self-Doubt and Recovery
Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such…
Reinforcement LearningValue prediction