DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning
arXiv:2602.16742v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been shown effective in enhancing the visual reflection and reasoning capabilities of Large Multimodal Models (LMMs). However, existing datasets are predominantly derived from either small-scale manual construction or...
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
arXiv:2602.16745v1 Announce Type: new Abstract: Test-time scaling can improve model performance by aggregating stochastic reasoning trajectories. However, achieving sample-efficient test-time self-consistency under a limited budget remains an open challenge. We introduce PETS (Principled and Efficient Test-TimeSelf-Consistency), which initiates a principled...
Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking
arXiv:2602.16746v1 Announce Type: new Abstract: Grokking -- the delayed transition from memorization to generalization in small algorithmic tasks -- remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of attention weight...
TopoFlow: Physics-guided Neural Networks for high-resolution air quality prediction
arXiv:2602.16821v1 Announce Type: new Abstract: We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography...
VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study
arXiv:2602.16833v1 Announce Type: new Abstract: Exploration remains a key bottleneck for reinforcement learning (RL) post-training of large language models (LLMs), where sparse feedback and large action spaces can lead to premature collapse into repetitive behaviors. We propose Verbalized Action Masking...
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
arXiv:2602.16947v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely...
Early-Warning Signals of Grokking via Loss-Landscape Geometry
arXiv:2602.16967v1 Announce Type: new Abstract: Grokking -- the abrupt transition from memorization to generalization after prolonged training -- has been linked to confinement on low-dimensional execution manifolds in modular arithmetic. Whether this mechanism extends beyond arithmetic remains open. We study...
Fail-Closed Alignment for Large Language Models
arXiv:2602.16977v1 Announce Type: new Abstract: We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant feature$-$via prompt-based jailbreaks$-$can cause...
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
arXiv:2602.17025v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is effective for training language models on complex reasoning. However, since the objective is defined relative to a group of sampled trajectories, extended deliberation can create more chances to realize...
Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum
arXiv:2602.17080v1 Announce Type: new Abstract: Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability, Muon utilizes the weight...
FLoRG: Federated Fine-tuning with Low-rank Gram Matrices and Procrustes Alignment
arXiv:2602.17095v1 Announce Type: new Abstract: Parameter-efficient fine-tuning techniques such as low-rank adaptation (LoRA) enable large language models (LLMs) to adapt to downstream tasks efficiently. Federated learning (FL) further facilitates this process by enabling collaborative fine-tuning across distributed clients without sharing...
Anthropic-funded group backs candidate attacked by rival AI super PAC
Dueling pro-AI PACs have centered around backing or targeting one New York congressional bid: Alex Bores, whose RAISE Act requires AI developers to disclose safety protocols and report serious system misuse.
Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis
arXiv:2602.15909v1 Announce Type: cross Abstract: Deep learning-based respiratory auscultation is currently hindered by two fundamental challenges: (i) inherent information loss, as converting signals into spectrograms discards transient acoustic events and clinical context; (ii) limited data availability, exacerbated by severe class...
Gated Tree Cross-attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs
arXiv:2602.15846v1 Announce Type: new Abstract: Decoder-only large language models achieve strong broad performance but are brittle to minor grammatical perturbations, undermining reliability for downstream reasoning. However, directly injecting explicit syntactic structure into an existing checkpoint can interfere with its pretrained...
Multi-source Heterogeneous Public Opinion Analysis via Collaborative Reasoning and Adaptive Fusion: A Systematically Integrated Approach
arXiv:2602.15857v1 Announce Type: new Abstract: The analysis of public opinion from multiple heterogeneous sources presents significant challenges due to structural differences, semantic variations, and platform-specific biases. This paper introduces a novel Collaborative Reasoning and Adaptive Fusion (CRAF) framework that systematically...
Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches
arXiv:2602.15869v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong performance on clinical de-identification, the task of identifying sensitive identifiers to protect privacy. However, previous work has not examined their generalizability between formats, cultures, and genders. In this...
MultiCube-RAG for Multi-hop Question Answering
arXiv:2602.15898v1 Announce Type: new Abstract: Multi-hop question answering (QA) necessitates multi-step reasoning and retrieval across interconnected subjects, attributes, and relations. Existing retrieval-augmented generation (RAG) methods struggle to capture these structural semantics accurately, resulting in suboptimal performance. Graph-based RAGs structure such...
Surgical Activation Steering via Generative Causal Mediation
arXiv:2602.16080v1 Announce Type: new Abstract: Where should we intervene in a language model (LM) to control behaviors that are diffused across many tokens of a long-form response? We introduce Generative Causal Mediation (GCM), a procedure for selecting model components, e.g.,...
Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
arXiv:2602.16144v1 Announce Type: new Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for...
Beyond Learning: A Training-Free Alternative to Model Adaptation
arXiv:2602.16189v1 Announce Type: new Abstract: Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-intensive, highlighting the need for alternatives that enable immediate action. We assume that each...
The Validity of Coreference-based Evaluations of Natural Language Understanding
arXiv:2602.16200v1 Announce Type: new Abstract: In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or conflicting....
Are LLMs Ready to Replace Bangla Annotators?
arXiv:2602.16241v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as automated annotators to scale dataset creation, yet their reliability as unbiased annotators--especially for low-resource and identity-sensitive settings--remains poorly understood. In this work, we study the behavior of...
BamaER: A Behavior-Aware Memory-Augmented Model for Exercise Recommendation
arXiv:2602.15879v1 Announce Type: new Abstract: Exercise recommendation focuses on personalized exercise selection conditioned on students' learning history, personal interests, and other individualized characteristics. Despite notable progress, most existing methods represent student learning solely as exercise sequences, overlooking rich behavioral interaction...
Distributed physics-informed neural networks via domain decomposition for fast flow reconstruction
arXiv:2602.15883v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure fields. However, scaling such models to large...
B-DENSE: Branching For Dense Ensemble Network Learning
arXiv:2602.15971v1 Announce Type: new Abstract: Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory steps. This...
Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks
arXiv:2602.15997v1 Announce Type: new Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across five model scales (405K-85M parameters), 120+ emergence events in eight algorithmic tasks, and three Pythia language models (160M-2.8B). We find:...
AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models
arXiv:2602.16042v1 Announce Type: new Abstract: As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical societal concern. Existing benchmarks overwhelmingly focus on standard performance metrics such as accuracy, BLEU, or...
MoE-Spec: Expert Budgeting for Efficient Speculative Decoding
arXiv:2602.16052v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large draft trees activate many unique experts, significantly increasing...
Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training
arXiv:2602.16065v1 Announce Type: new Abstract: Generative Artificial Intelligence (AI), such as large language models (LLMs), has become a transformative force across science, industry, and society. As these systems grow in popularity, web data becomes increasingly interwoven with this AI-generated material...
On the Power of Source Screening for Learning Shared Feature Extractors
arXiv:2602.16125v1 Announce Type: new Abstract: Learning with shared representation is widely recognized as an effective way to separate commonalities from heterogeneity across various heterogeneous sources. Most existing work includes all related data sources via simultaneously training a common feature extractor...