2/25/2026
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Survey examining terminology, definitions, and taxonomy of data agents—autonomous systems orchestrating data and AI for complex data tasks.
2/25/2026
Repurposing Synthetic Data for Fine-grained Search Agent Supervision
LLM-based search agents trained on synthetic entity-centric data using improved reward mechanisms to capture informative near-miss samples.
2/25/2026
A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
Brain visual decoding from fMRI using hierarchical architecture for subject-agnostic reconstruction without subject-specific training.
2/25/2026
OckBench: Measuring the Efficiency of LLM Reasoning
OckBench: Benchmark measuring LLM reasoning efficiency via token usage, revealing up to 5x differences in token length across models.
2/25/2026
Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
Data-efficient fine-tuning strategy for adding controllable parameters to text-to-video diffusion models using synthetic data.
2/25/2026
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Refusal Steering: Inference-time method for fine-grained control over LLM refusal behavior on sensitive topics without retraining.
2/25/2026
HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment
HiGR: Generative slate recommendation system using hierarchical planning and multi-objective preference alignment for ranked lists.
2/25/2026
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
CogFlow: Multimodal LLM system for visual math problem solving improving visual perception integration and reasoning.
2/25/2026
What Matters For Safety Alignment?
Comprehensive empirical study evaluating factors affecting safety alignment in LLMs and LRMs across 32 recent models.
2/25/2026
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Fast-ThinkAct: Efficient Vision-Language-Action framework reducing inference latency through verbalizable latent planning.
2/25/2026
CLiMB: A Domain-Informed Novelty Detection Clustering Framework for Galactic Archaeology and Scientific Discovery
CLiMB: Domain-informed clustering framework for novelty detection in scientific discovery with application to galactic archaeology.
2/25/2026
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Molmo2: Open-weight vision-language model with video understanding, grounding, and disclosed training data and recipe.
2/25/2026
Generating metamers of human scene understanding
MetamerGen: Latent diffusion model generating visual scenes aligned with human perception using periphery gist and foveal information.
2/25/2026
PhysE-Inv: A Physics-Encoded Inverse Modeling approach for Arctic Snow Depth Prediction
Physics-encoded inverse modeling approach combining sequential architecture with physics constraints for Arctic snow depth prediction.
2/25/2026
FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
FROST: Attention-aware pruning method for efficient LLM reasoning by identifying and removing reasoning outliers while preserving capacity.
2/25/2026
When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applications
Persona Brainstorm Audit method for detecting bias and fairness issues in open-ended creative outputs from LLMs.
2/25/2026
CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models
CryoLVM applies self-supervised learning with vision models to cryo-EM density maps for structural biology analysis.
2/25/2026
Do We Need Adam? Surprisingly Strong and Sparse Reinforcement Learning with SGD in LLMs
Study showing SGD with sparsity outperforms Adam for RL from verifiable reward in LLM training, challenging standard optimization practices.
2/25/2026
AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
AceGRPO: Reinforcement learning agent for autonomous ML engineering using adaptive curriculum and group relative policy optimization to overcome parameter freezing.
2/25/2026
Language Modeling and Understanding Through Paraphrase Generation and Detection
Study on paraphrase generation and detection as mechanisms for language understanding and modeling in neural networks.
2/25/2026
GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing
GOT-Edit improves object tracking in video by incorporating 3D geometric cues and semantic reasoning alongside 2D features.
2/25/2026
SAS-Net: Scene-Appearance Separation Network for Robust Spatiotemporal Registration in Bidirectional Photoacoustic Microscopy
SAS-Net addresses spatiotemporal misalignment in bidirectional photoacoustic microscopy using scene-appearance separation for medical imaging.
2/25/2026
UI-Venus-1.5 Technical Report
UI-Venus-1.5: GUI agent with 2B, 8B, and 30B-A3B variants for automating digital environment interactions with broad generality and strong task performance.
2/25/2026
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
VESPO: reinforcement learning method for training LLMs with improved stability through soft policy optimization and importance sampling to address policy divergence.
2/25/2026
KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
KBVQ-MoE: compression technique for Mixture of Experts LLMs using vector quantization and SVD to reduce parameter size and memory for resource-constrained deployment.
2/25/2026
PMG: Parameterized Motion Generator for Human-like Locomotion Control
PMG algorithm for humanoid locomotion using parameterized motion generation with trajectory-following control.
2/25/2026
Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction
Sim2Radar uses VLM-guided scene reconstruction to synthesize radar training data from RGB images, addressing radar dataset scarcity.
2/25/2026
Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference
Pawsterior framework extending variational flow matching for simulation-based inference with structured domains and physical constraints.
2/25/2026
Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment
Identifies and analyzes 'silent inconsistency' problem in data-parallel LLM fine-tuning where gradient synchronization doesn't ensure worker-level optimization alignment.
2/25/2026
ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies
ST-EVO framework for self-evolving LLM-powered multi-agent systems that dynamically construct task-adaptive communication topologies instead of predefined structures.
2/25/2026
Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks
Studies mechanical basis of capability emergence in neural networks across scales 405K-85M parameters, finding scale-invariant representation collapse and top-down reorganization.
2/25/2026
AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models
Proposes AI-CARE metric incorporating carbon emissions and energy consumption alongside standard performance metrics for ML model evaluation.
2/25/2026
AI-Driven Structure Refinement of X-ray Diffraction
Applies physics-constrained whole-pattern expectation-maximization algorithm for AI-driven refinement of X-ray diffraction crystal structures.
2/25/2026
Intent Laundering: AI Safety Datasets Are Not What They Seem
Analyzes quality issues in AI safety datasets, finding they rely on superficial 'triggering cues' rather than genuine adversarial patterns.
2/25/2026
AI-Mediated Feedback Improves Student Revisions: A Randomized Trial with FeedbackWriter in a Large Undergraduate Course
Randomized trial showing AI-generated feedback suggestions via FeedbackWriter improve student revisions when reviewed by human TAs in economics course.
2/25/2026
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
Proposes symbolic alternative to GNN message-passing for more interpretable and expressive graph learning in high-stakes domains.
2/25/2026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
MASPO algorithm improves LLM reasoning through reinforcement learning with verifiable rewards, addressing gradient utilization and probability mass issues in existing RLVR methods.
2/25/2026
Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis
ML method using random walk learning on cortical similarity networks for diagnosing Alzheimer's and Lewy body dementia.
2/25/2026
Games That Teach, Chats That Convince: Comparing Interactive and Static Formats for Persuasive Learning
User study comparing chatbots, games, and essays for persuasive learning on sustainability topics with identical content.
2/25/2026
Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation
Uses LLM-assisted reasoning to map 2D engineering drawing annotations to 3D CAD features for manufacturing automation and process planning.
2/25/2026
How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
Benchmark study (SP-ABCBench) evaluating whether LLM agents can simulate human security and privacy attitudes and behaviors for risk forecasting.
2/25/2026
Transforming Science Learning Materials in the Era of Artificial Intelligence
Examines integration of AI into science education materials, covering personalization, adaptive instruction, and accessibility in K-12 learning contexts.
2/25/2026
RPU -- A Reasoning Processing Unit
Proposes Reasoning Processing Unit (RPU) architecture to address memory bandwidth bottlenecks in LLM inference, particularly for reasoning applications with long outputs.
2/25/2026
The Metaphysics We Train: A Heideggerian Reading of Machine Learning
Phenomenological analysis of ML through Heideggerian philosophy. Theoretical framework rather than technical or practical contribution.
2/25/2026
NEXUS: A compact neural architecture for high-resolution spatiotemporal air quality forecasting in Delhi National Capital Region
Neural spatiotemporal architecture for air quality forecasting in Delhi using four years of atmospheric data across sixteen spatial grids.
2/25/2026
When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
Study revealing performance degradation when using state-of-the-art text-to-image models as synthetic training data generators for vision tasks.
2/25/2026
A Very Big Video Reasoning Suite
Benchmark suite for evaluating video reasoning capabilities in modern video models including spatiotemporal reasoning and scaling behavior.
2/25/2026
Tensor Network Generator-Enhanced Optimization for Traveling Salesman Problem
Tensor network generator-enhanced optimization framework applying Born machines for solving traveling salesman problem combinatorial optimization.
2/25/2026
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Elastic LLMs
MoBiQuant enables elastic LLM deployment with token-adaptive mixture-of-bits quantization supporting dynamic precision switching at runtime.
2/25/2026
FedAvg-Based CTMC Hazard Model for Federated Bridge Deterioration Assessment
Federated learning framework for estimating continuous-time Markov chain hazard model of bridge deterioration without sharing raw inspection data.