MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
arXiv:2602.15206v1 Announce Type: new Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as...
Automatically Finding Reward Model Biases
arXiv:2602.15222v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce...
BindCLIP: A Unified Contrastive-Generative Representation Learning Framework for Virtual Screening
arXiv:2602.15236v1 Announce Type: new Abstract: Virtual screening aims to efficiently identify active ligands from massive chemical libraries for a given target pocket. Recent CLIP-style models such as DrugCLIP enable scalable virtual screening by embedding pockets and ligands into a shared...
Fast and Effective On-policy Distillation from Reasoning Prefixes
arXiv:2602.15260v1 Announce Type: new Abstract: On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy distillation....
Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization
arXiv:2602.15304v1 Announce Type: new Abstract: Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We present a hybrid privacy-preserving framework that combines Federated Learning (FL) and Split Learning (SL) to...
A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining
arXiv:2602.15330v1 Announce Type: new Abstract: The long-tail distribution, where a few head labels dominate while rare tail labels abound, poses a persistent challenge for large-scale Multi-Label Classification (MLC) in real-world data mining applications. Existing resampling and reweighting strategies often disrupt...
Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models
arXiv:2602.15332v1 Announce Type: new Abstract: Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens or spans correlated with an answer, but they rarely reveal where the model makes consequential reasoning turns,...
CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies
arXiv:2602.15367v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most existing approaches address these issues primarily...
Fairness over Equality: Correcting Social Incentives in Asymmetric Sequential Social Dilemmas
arXiv:2602.15407v1 Announce Type: new Abstract: Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by incorporating intrinsic drives that encourage...
Logit Distance Bounds Representational Similarity
arXiv:2602.15438v1 Announce Type: new Abstract: For a broad family of discriminative models that includes autoregressive language models, identifiability results imply that if two models induce the same conditional distributions, then their internal representations agree up to an invertible linear transformation....
Benchmarking IoT Time-Series AD with Event-Level Augmentations
arXiv:2602.15457v1 Announce Type: new Abstract: Anomaly detection (AD) for safety-critical IoT time series should be judged at the event level: reliability and earliness under realistic perturbations. Yet many studies still emphasize point-level results on curated base datasets, limiting value for...
POP: Prior-fitted Optimizer Policies
arXiv:2602.15473v1 Announce Type: new Abstract: Optimization refers to the task of finding extrema of an objective function. Classical gradient-based optimizers are highly sensitive to hyperparameter choices. In highly non-convex settings their performance relies on carefully tuned learning rates, momentum, and...
Evaluating Federated Learning for Cross-Country Mood Inference from Smartphone Sensing Data
arXiv:2602.15478v1 Announce Type: new Abstract: Mood instability is a key behavioral indicator of mental health, yet traditional assessments rely on infrequent and retrospective reports that fail to capture its continuous nature. Smartphone-based mobile sensing enables passive, in-the-wild mood inference from...
LLM-as-Judge on a Budget
arXiv:2602.15481v1 Announce Type: new Abstract: LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean...
The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
arXiv:2602.15515v1 Announce Type: new Abstract: Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation...
Uniform error bounds for quantized dynamical models
arXiv:2602.15586v1 Announce Type: new Abstract: This paper provides statistical guarantees on the accuracy of dynamical models learned from dependent data sequences. Specifically, we develop uniform error bounds that apply to quantized models and imperfect optimization algorithms commonly used in practical...
Multi-Objective Coverage via Constraint Active Search
arXiv:2602.15595v1 Announce Type: new Abstract: In this paper, we formulate the new multi-objective coverage (MOC) problem where our goal is to identify a small set of representative samples whose predicted outcomes broadly cover the feasible multi-objective space. This problem is...
Certified Per-Instance Unlearning Using Individual Sensitivity Bounds
arXiv:2602.15602v1 Announce Type: new Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative calibration often results in performance degradation, limiting practical applicability. In this work,...
Join the Largest Global Community in Computing
IEEE Computer Society is the top source for information, inspiration, and collaboration in computer science and engineering, empowering technologist worldwide
Is your startup’s check engine light on? Google Cloud’s VP explains what to do
Startup founders are being pushed to move faster than ever, using AI while facing tighter funding, rising infrastructure costs, and more pressure to show real traction early. Cloud credits, access to GPUs, and foundation models have made it easier to...
Google Cloud’s VP for startups on reading your ‘check engine light’ before it’s too late
Startup founders are being pushed to move faster than ever, using AI while facing tighter funding, rising infrastructure costs, and more pressure to show real traction early. Cloud credits, access to GPUs, and foundation models have made it easier to...
OpenAI pushes into higher education as India seeks to scale AI skills
OpenAI says its India education partnerships aim to reach more than 100,000 students, faculty, and staff over the next year.
Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
arXiv:2602.14069v1 Announce Type: new Abstract: Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to brittleness and reward hacking in open-ended alignment. We argue that robust alignment for non-verifiable tasks...
Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
arXiv:2602.14073v1 Announce Type: new Abstract: Most vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts. This restricts their usability for non-English-speaking users and hinders the development of multimodal systems that reflect diverse...
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
arXiv:2602.14080v1 Announce Type: new Abstract: Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (lost keys). We propose a behavioral framework that profiles factual...
Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering
arXiv:2602.14162v1 Announce Type: new Abstract: Existing multimodal document question answering methods universally adopt a supply-side ingestion strategy: running a Vision-Language Model (VLM) on every page during indexing to generate comprehensive descriptions, then answering questions through text retrieval. However, this "pre-ingestion"...