Bases of Steerable Kernels for Equivariant CNNs: From 2D Rotations to the Lorentz Group
arXiv:2603.12459v1 Announce Type: new Abstract: We present an alternative way of solving the steerable kernel constraint that appears in the design of steerable equivariant convolutional neural networks. We find explicit real and complex bases which are ready to use, for...
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
arXiv:2603.12634v1 Announce Type: new Abstract: Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end trajectories....
Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation
arXiv:2603.11342v1 Announce Type: new Abstract: The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the...
Streaming Translation and Transcription Through Speech-to-Text Causal Alignment
arXiv:2603.11578v1 Announce Type: new Abstract: Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs simultaneous speech-to-text translation and streaming transcription...
Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
arXiv:2603.11052v1 Announce Type: new Abstract: Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncertainty due to finite data, imperfect optimization, and distribution shift. For practical deployment...
Graph Tokenization for Bridging Graphs and Transformers
arXiv:2603.11099v1 Announce Type: new Abstract: The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph...
Reference-Guided Machine Unlearning
arXiv:2603.11210v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or random labeling. However, these...
ZTab: Domain-based Zero-shot Annotation for Table Columns
arXiv:2603.11436v1 Announce Type: new Abstract: This study addresses the challenge of automatically detecting semantic column types in relational tables, a key task in many real-world applications. Zero-shot modeling eliminates the need for user-provided labeled training data, making it ideal for...
Bridging Discrete Marks and Continuous Dynamics: Dual-Path Cross-Interaction for Marked Temporal Point Processes
arXiv:2603.11462v1 Announce Type: new Abstract: Predicting irregularly spaced event sequences with discrete marks poses significant challenges due to the complex, asynchronous dependencies embedded within continuous-time data streams.Existing sequential approaches capture dependencies among event tokens but ignore the continuous evolution between...
The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments
arXiv:2603.10130v1 Announce Type: new Abstract: Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and retrieval, yielding a prediction-measurement gap:...
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
arXiv:2603.10145v1 Announce Type: new Abstract: The last layer of neural language models (LMs) projects output features of dimension $D$ to logits in dimension $V$, the size of the vocabulary, where usually $D \ll V$. This mismatch is known to raise...
A Survey of Weight Space Learning: Understanding, Representation, and Generation
arXiv:2603.10090v1 Announce Type: new Abstract: Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances show that the set of all possible weight values...
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
arXiv:2603.10156v1 Announce Type: new Abstract: Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or...
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
arXiv:2603.10379v1 Announce Type: new Abstract: This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-layers. As MoE architectures have emerged as an efficient method...
AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents
arXiv:2603.09716v1 Announce Type: new Abstract: Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context usage, which jointly limit adaptability in open-ended...
LooComp: Leverage Leave-One-Out Strategy to Encoder-only Transformer for Efficient Query-aware Context Compression
arXiv:2603.09222v1 Announce Type: new Abstract: Efficient context compression is crucial for improving the accuracy and scalability of question answering. For the efficiency of Retrieval Augmented Generation, context should be delivered fast, compact, and precise to ensure clue sufficiency and budget-friendly...
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
arXiv:2603.09463v1 Announce Type: new Abstract: Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain combinations of task-specialist...
N-gram-like Language Models Predict Reading Time Best
arXiv:2603.09872v1 Announce Type: new Abstract: Recent work has found that contemporary language models such as transformers can become so good at next-word prediction that the probabilities they calculate become worse for predicting reading time. In this paper, we propose that...
BiCLIP: Domain Canonicalization via Structured Geometric Transformation
arXiv:2603.08942v1 Announce Type: cross Abstract: Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that independently trained VLMs are related by...
Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting
arXiv:2603.09085v1 Announce Type: new Abstract: By capturing the prevailing sentiment and market mood, textual data has become increasingly vital for forecasting commodity prices, particularly in metal markets. However, the effectiveness of lightweight, finetuned large language models (LLMs) in extracting predictive...
$P^2$GNN: Two Prototype Sets to boost GNN Performance
arXiv:2603.09195v1 Announce Type: new Abstract: Message Passing Graph Neural Networks (MP-GNNs) have garnered attention for addressing various industry challenges, such as user recommendation and fraud detection. However, they face two major hurdles: (1) heavy reliance on local context, often lacking...
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
arXiv:2603.09221v1 Announce Type: new Abstract: Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode....
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
arXiv:2603.06923v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training which is inefficient and unable to...
Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
arXiv:2603.06592v1 Announce Type: new Abstract: Contemporary studies have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models. Building a robust, unified understanding of these phenomena requires disassembling a model within the scope of its training. While...
RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts
arXiv:2603.07366v1 Announce Type: new Abstract: Many errors in student essays can be explained by influence from the native language (L1). L1 interference refers to errors influenced by a speaker's first language, such as using stadion instead of stadium, reflecting lexical...
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...
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...
LegoNet: Memory Footprint Reduction Through Block Weight Clustering
arXiv:2603.06606v1 Announce Type: new Abstract: As the need for neural network-based applications to become more accurate and powerful grows, so too does their size and memory footprint. With embedded devices, whose cache and RAM are limited, this growth hinders their...
Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
arXiv:2603.06728v1 Announce Type: new Abstract: Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet this accelerator remains largely unused for large language model workloads. CoreML, Apple's public ML framework,...
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
arXiv:2603.06729v1 Announce Type: new Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical...