2/27/2026
VeRO: An Evaluation Harness for Agents to Optimize Agents
VeRO: Evaluation framework for assessing coding agents that optimize other agents through iterative edit-execute-evaluate cycles.
2/27/2026
Flow Matching is Adaptive to Manifold Structures
Flow matching generative model that adapts to manifold structures, offering simulation-free alternative to diffusion models.
2/27/2026
From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference
Theoretical analysis of scaling limits from shallow Bayesian neural networks to Gaussian processes with scalable inference methods.
2/27/2026
Towards Dynamic Dense Retrieval with Routing Strategy
Dynamic dense retrieval with routing strategy for adapting information retrieval models across domains without full retraining.
2/27/2026
CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
CourtGuard: Model-agnostic multi-agent framework for zero-shot LLM safety policy adaptation using retrieval-augmented debate.
2/27/2026
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Search-P1: Path-centric reward shaping for training agentic RAG systems with improved sample efficiency via RL.
2/27/2026
Correcting Human Labels for Rater Effects in AI Evaluation: An Item Response Theory Approach
Item Response Theory approach to correct systematic rater biases in human evaluations for AI model assessment.
2/27/2026
SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
SideQuest: Model-driven KV cache management technique for long-context agentic reasoning tasks with multi-hop retrieval.
2/27/2026
Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problems
Hybrid ML framework combining autoencoders and transformers for accelerator beam diagnostics simulations.
2/27/2026
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Trie-based constrained decoding optimization for LLM generative retrieval on accelerators. Improves business logic constraints in recommendations.
2/27/2026
dLLM: Simple Diffusion Language Modeling
dLLM: Unified framework for diffusion language models. Standardizes components across research implementations for reproducibility.
2/27/2026
Generative Recommendation for Large-Scale Advertising
GR4AD: Production generative recommendation system for large-scale advertising using LLMs. Architecture, learning, and serving optimization.
2/27/2026
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
AMA-Bench: Benchmark evaluating long-horizon memory for LLM-based agentic applications. Addresses gap between dialogue benchmarks and real agent scenarios.
2/27/2026
QSIM: Mitigating Overestimation in Multi-Agent Reinforcement Learning via Action Similarity Weighted Q-Learning
QSIM: Multi-agent reinforcement learning method addressing Q-value overestimation via action similarity weighting. Value decomposition improvement.
2/27/2026
Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
Research on diffusion models for end-to-end autonomous driving in real-world settings. arXiv paper exploring decision-making applications.
2/27/2026
TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
TARAZ benchmark for evaluating cultural competence of LLMs in Persian with short-answer format and morphological analysis.
2/27/2026
Unsupervised Continual Learning for Amortized Bayesian Inference
Unsupervised continual learning framework for amortized Bayesian inference handling sequential data and distribution shifts.
2/27/2026
SPD Learn: A Geometric Deep Learning Python Library for Neural Decoding Through Trivialization
SPD Learn Python library for symmetric positive definite matrix neural networks in neural decoding with geometric deep learning.
2/27/2026
OmniGAIA: Towards Native Omni-Modal AI Agents
OmniGAIA benchmark for evaluating omni-modal AI agents with unified vision, audio, and language perception capabilities.
2/27/2026
SIGMA: A Semantic-Grounded Instruction-Driven Generative Multi-Task Recommender at AliExpress
SIGMA system applying LLMs to multi-task recommendation at scale, handling diverse business requirements beyond traditional next-item prediction.
2/27/2026
pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation
Parameter-efficient fine-tuning combining multiple domain expert models for visual adaptation tasks via prompt tuning.
2/27/2026
MoDora: Tree-Based Semi-Structured Document Analysis System
Tree-based system for analyzing semi-structured documents with mixed content types enabling question-answering over complex layouts.
2/27/2026
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
LLM agent framework (SALA) for evaluating deanonymization risks through stylometry-assisted analysis of textual data with interpretable pipeline.
2/27/2026
Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
Study of information-theoretic limits in multimodal LLMs showing modality-specific information is discarded during decoding despite surviving encoding layers.
2/27/2026
FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classification
arXiv paper: Fairness-aware mixed-precision quantization for neural network compression in medical imaging, explicitly addressing algorithmic fairness during model compression.
2/27/2026
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
arXiv paper: Theoretical analysis of fine-tuning effects on in-context learning in linear attention transformers, balancing downstream and few-shot task performance.
2/27/2026
Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction
arXiv paper: Plug-and-play diffusion framework with ADMM for medical image reconstruction addressing memory issues in PnP solvers.
2/27/2026
Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
arXiv paper: Large-scale app store search ranking system augmented with LLM-generated textual relevance judgments to address scarcity of expert labels.
2/27/2026
Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
arXiv paper: Zeroth-order optimization for leader-follower Stackelberg control in combinatorial congestion games with discrete strategy selection.
2/27/2026
ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
arXiv paper: Training-free hierarchical manifold guidance for dataset distillation using diffusion models without requiring gradient computation.
2/27/2026
Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction
arXiv paper: Zero-shot and one-shot adaptation of small language models for leader-follower role assignment in human-robot interaction with resource constraints.
2/27/2026
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Analyzes parameter-efficient fine-tuning for continual learning using Neural Tangent Kernel theory to understand model adaptation and catastrophic forgetting mitigation.
2/27/2026
Efficient Graph Coloring with Neural Networks: A Physics-Inspired Approach for Large Graphs
Physics-inspired neural framework using graph neural networks to solve large-scale graph coloring combinatorial optimization problems near algorithmic phase transitions.
2/27/2026
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
Proposes label unlearning method for vertical federated learning using representation-level manifold mixup to enable privacy-preserving model unlearning.
2/27/2026
Beyond Attribution: Unified Concept-Level Explanations
Model-agnostic explanation technique integrating concept-based approaches with diverse explanation forms beyond attribution methods.
2/27/2026
Aligning Few-Step Diffusion Models with Dense Reward Difference Learning
Reinforcement learning framework for aligning few-step diffusion models with downstream objectives using stepwise policy optimization.
2/27/2026
Neuro-Symbolic AI for Analytical Solutions of Differential Equations
Neuro-symbolic framework automating discovery of analytical solutions to differential equations using formal grammars and continuous search.
2/27/2026
Sample Compression for Self Certified Continual Learning
Continual learning method using sample compression theory to provide computable guarantees while avoiding catastrophic forgetting.
2/27/2026
Large Language Model Compression with Global Rank and Sparsity Optimization
Compression technique for large language models using global rank and sparsity optimization with layer-wise weight allocation.
2/27/2026
FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
Large-scale benchmark for evaluating machine learning solvers on combinatorial optimization using real-world industrial datasets.
2/27/2026
RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
Research on whether language models can learn to evade latent-space safety monitors, with implications for LLM alignment and security.
2/27/2026
Skewed Score: A statistical framework to assess autograders
Statistical framework for evaluating LLM-as-a-judge systems, addressing reliability and bias issues in automated LLM output evaluation.
2/27/2026
Zero-Variance Gradients for Variational Autoencoders
Silent Gradients approach for training VAEs by restricting decoder architecture to reduce gradient estimation variance.
2/27/2026
Online time series prediction using feature adjustment
Online time series forecasting method using feature adjustment to handle distribution shift in sequential data deployment.
2/27/2026
Predicting LLM Reasoning Performance with Small Proxy Model
rBridge framework enabling small proxy models (≤1B params) to predict reasoning performance of larger LLMs, optimizing dataset scaling.
2/27/2026
Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
Theoretical analysis of softmax attention mechanisms in LLMs through single-location regression task, addressing why softmax dominates alternative activation functions.
2/27/2026
Compute-Optimal Quantization-Aware Training
Study of compute-optimal allocation between full-precision and quantization-aware training phases for neural networks.
2/27/2026
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
Dynamic safety monitoring system for LLMs that adaptively adjusts computation based on input difficulty.
2/27/2026
Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Method for improving masked diffusion models by learning better unmasking policies beyond rule-based position scheduling.
2/27/2026
Learning to Answer from Correct Demonstrations
Imitation learning approach for training models with multiple acceptable answers from limited correct demonstrations.