Cross-Modal Taxonomic Generalization in (Vision-) Language Models
arXiv:2603.07474v1 Announce Type: new Abstract: What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grounded evidence? We study this question for a scenario where part of the input...
Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs
arXiv:2603.07475v1 Announce Type: new Abstract: Autoregressive (AR) language models form representations incrementally through left-to-right prediction, whereas diffusion language models (dLLMs) are trained via full-sequence denoising. Although recent dLLMs match AR performance, it remains unclear whether diffusion objectives fundamentally reshape internal...
A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text
arXiv:2603.07487v1 Announce Type: new Abstract: Clinical information extraction (e.g., 2010 i2b2/VA challenge) usually presents tasks of concept recognition, assertion classification, and relation extraction. Jointly modeling the multi-stage tasks in the clinical domain is an underexplored topic. The existing independent task...
Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
arXiv:2603.07513v1 Announce Type: new Abstract: Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive...
TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning
arXiv:2603.07528v1 Announce Type: new Abstract: Table reasoning requires models to jointly perform semantic understanding and precise numerical operations. Most existing methods rely on a single-turn reasoning paradigm over tables which suffers from context overflow and weak numerical sensitivity. To address...
Learning-free L2-Accented Speech Generation using Phonological Rules
arXiv:2603.07550v1 Announce Type: new Abstract: Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that...
Nw\=ach\=a Mun\=a: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
arXiv:2603.07554v1 Announce Type: new Abstract: Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nw\=ach\=a Mun\=a, a newly curated 5.39-hour manually transcribed...
Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types
arXiv:2603.07755v1 Announce Type: new Abstract: A geometric hallucination taxonomy distinguishes three failure types -- center-drift (Type~1), wrong-well convergence (Type~2), and coverage gaps (Type~3) -- by their signatures in embedding cluster space. Prior work found Types~1 and~2 indistinguishable in full-dimensional contextual...
QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis
arXiv:2603.07766v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs)...
Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems
arXiv:2603.07779v1 Announce Type: new Abstract: Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing and difficulty scaling. We introduce a four-stage...
Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context
arXiv:2603.07792v1 Announce Type: new Abstract: Large language models (LLMs) increasingly influence global digital ecosystems, yet their potential to perpetuate social and cultural biases remains poorly understood in underrepresented contexts. This study presents a systematic analysis of representational biases in seven...
An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data
arXiv:2603.07841v1 Announce Type: new Abstract: Recent advances in large language models has strengthened Text2SQL systems that translate natural language questions into database queries. A persistent deployment challenge is to assess a newly trained Text2SQL system on an unseen and unlabeled...
How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective
arXiv:2603.06591v1 Announce Type: new Abstract: Large Language Models (LLMs) often allocate disproportionate attention to specific tokens, a phenomenon commonly referred to as the attention sink. While such sinks are generally considered detrimental, prior studies have identified a notable exception: the...
Switchable Activation Networks
arXiv:2603.06601v1 Announce Type: new Abstract: Deep neural networks, and more recently large-scale generative models such as large language models (LLMs) and large vision-action models (LVAs), achieve remarkable performance across diverse domains, yet their prohibitive computational cost hinders deployment in resource-constrained...
Khatri-Rao Clustering for Data Summarization
arXiv:2603.06602v1 Announce Type: new Abstract: As datasets continue to grow in size and complexity, finding succinct yet accurate data summaries poses a key challenge. Centroid-based clustering, a widely adopted approach to address this challenge, finds informative summaries of datasets in...
Scale Dependent Data Duplication
arXiv:2603.06603v1 Announce Type: new Abstract: Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what constitutes a ``duplicate'': beyond surface-form matches, semantically equivalent documents (e.g. translations) may...
Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection
arXiv:2603.06604v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in critical decision-making systems, the lack of reliable methods to measure their uncertainty presents a fundamental trustworthiness risk. We introduce a normalized confidence score based on output...
Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series
arXiv:2603.06605v1 Announce Type: new Abstract: Electronic health records (EHR) are irregular, asynchronous multivariate time series. As time-series foundation models increasingly tokenize events rather than discretizing time, the input layout becomes a key design choice. Grids expose time$\times$variable structure but require...
Valid Feature-Level Inference for Tabular Foundation Models via the Conditional Randomization Test
arXiv:2603.06609v1 Announce Type: new Abstract: Modern machine learning models are highly expressive but notoriously difficult to analyze statistically. In particular, while black-box predictors can achieve strong empirical performance, they rarely provide valid hypothesis tests or p-values for assessing whether individual...
OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence
arXiv:2603.06613v1 Announce Type: new Abstract: This paper presents OptiRoulette, a stochastic meta-optimizer that selects update rules during training instead of fixing a single optimizer. The method combines warmup optimizer locking, random sampling from an active optimizer pool, compatibility-aware learning-rate scaling...
Correlation Analysis of Generative Models
arXiv:2603.06614v1 Announce Type: new Abstract: Based on literature review about existing diffusion models and flow matching with a neural network to predict a predefined target from noisy data, a unified representation is first proposed for these models using two simple...
Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
arXiv:2603.06615v1 Announce Type: new Abstract: For multivariate co-generation in scientific applications, we advocate pairwise block rather than joint modeling of all variables. This design mitigates the computational burden and data imbalance. To this end, we propose an Annealed Co-Generation (ACG)...
Distilling and Adapting: A Topology-Aware Framework for Zero-Shot Interaction Prediction in Multiplex Biological Networks
arXiv:2603.06618v1 Announce Type: new Abstract: Multiplex Biological Networks (MBNs), which represent multiple interaction types between entities, are crucial for understanding complex biological systems. Yet, existing methods often inadequately model multiplexity, struggle to integrate structural and sequence information, and face difficulties...
Not all tokens are needed(NAT): token efficient reinforcement learning
arXiv:2603.06619v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout...
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
arXiv:2603.06621v1 Announce Type: new Abstract: Process Reward Models (PRMs) are rapidly becoming the backbone of LLM reasoning pipelines, yet we demonstrate that state-of-the-art PRMs are systematically exploitable under adversarial optimization pressure. To address this, we introduce a three-tiered diagnostic framework...
From ARIMA to Attention: Power Load Forecasting Using Temporal Deep Learning
arXiv:2603.06622v1 Announce Type: new Abstract: Accurate short-term power load forecasting is important to effectively manage, optimize, and ensure the robustness of modern power systems. This paper performs an empirical evaluation of a traditional statistical model and deep learning approaches for...
Advances in GRPO for Generation Models: A Survey
arXiv:2603.06623v1 Announce Type: new Abstract: Large-scale flow matching models have achieved strong performance across generative tasks such as text-to-image, video, 3D, and speech synthesis. However, aligning their outputs with human preferences and task-specific objectives remains challenging. Flow-GRPO extends Group Relative...
Pavement Missing Condition Data Imputation through Collective Learning-Based Graph Neural Networks
arXiv:2603.06625v1 Announce Type: new Abstract: Pavement condition data is important in providing information regarding the current state of the road network and in determining the needs of maintenance and rehabilitation treatments. However, the condition data is often incomplete due to...
Grouter: Decoupling Routing from Representation for Accelerated MoE Training
arXiv:2603.06626v1 Announce Type: new Abstract: Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneously train expert weights while searching for an optimal routing policy within a vast combinatorial space. This entanglement often leads...
A new Uncertainty Principle in Machine Learning
arXiv:2603.06634v1 Announce Type: new Abstract: Many scientific problems in the context of machine learning can be reduced to the search of polynomial answers in appropriate variables. The Hevisidization of arbitrary polynomial is actually provided by one-and-the same two-layer expression. What...