5/18/2026
What Is Preference Optimization Doing, and Why?
Analysis of optimization dynamics comparing preference optimization methods like DPO and PPO for LLM alignment.
5/18/2026
Graph-Regularized Sparse Autoencoders for LLM Safety Steering
Graph-regularized sparse autoencoders for extracting and steering safety behaviors in LLMs during inference.
5/18/2026
T2T-LA: A Topology-to-Topology LLM Agent for Graph Learning with Neither Feature Access nor Task Knowledge
LLM agent that learns graph construction rules from topology data without feature access or task knowledge for CAD applications.
5/18/2026
LASER: Language Model Regression for Semi-Structured Workflow Resource and Runtime Estimation
Language model based approach for predicting resource consumption and runtime in cloud workflows using semi-structured job configurations.
5/18/2026
Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
Method for extreme 1-bit quantization of LLMs using output alignment techniques to enable deployment on resource-constrained devices.
5/18/2026
Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities
Studies representation misdirection in LLM unlearning revealing controllable side behaviors via latent vectors
5/18/2026
ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
Foundation model for zero-shot feature importance estimation in tabular data without model access
5/18/2026
Antidistillation Fingerprinting
Fingerprinting method to detect when student LLMs trained on teacher model outputs via distillation
5/18/2026
Online Vector Quantized Attention
Vector quantized attention layer balancing efficiency and performance for long context language models
5/18/2026
BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
Bit-plane decomposition quantization enabling 2-3 bit inference for large language models
5/18/2026
Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment
Geometric anchoring approach for DPO addressing reference policy miscalibration in LLM alignment
5/18/2026
Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution
PEPO algorithm for Direct Preference Optimization mitigating over-optimization without reward models
5/18/2026
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Unified system combining reinforcement learning with adaptive speculative decoding for efficient LLM serving
5/18/2026
Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
Chain-of-thought compression method for LLMs achieving high-fidelity reasoning with extreme compression ratios
5/18/2026
Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs
Explains neural network compression using algorithmic complexity lens via mosaic-of-motifs pattern analysis
5/18/2026
SGNO: Spectral Generator Neural Operators for Stable Long Horizon PDE Rollouts
Neural PDE surrogates using spectral methods to reduce error accumulation in long-horizon predictions
5/18/2026
Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Layer gradient analysis method for identifying optimal layers to edit in LLMs, improving knowledge editing performance across samples.
5/18/2026
Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis
Stock prediction combining node transformers with BERT sentiment analysis. Financial ML application with limited novelty.
5/18/2026
Mechanisms of Introspective Awareness
Study of how LLMs detect and identify injected steering vectors in residual streams, revealing introspective awareness mechanisms.
5/18/2026
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Research on internalizing skills within LLM agents through in-context reinforcement learning, reducing token overhead and retrieval noise.
5/18/2026
DMax: Aggressive Parallel Decoding for dLLMs
DMax paradigm for efficient parallel decoding in diffusion language models via progressive self-refinement, reducing error accumulation.
5/18/2026
KV Cache Offloading for Context-Intensive Tasks
Research on KV cache offloading to reduce memory and latency bottlenecks for long-context LLM inference tasks.
5/18/2026
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Benchmark for evaluating LLMs' ability to reason about differential privacy algorithms, lowering barrier for DP application design.
5/18/2026
CAP: Controllable Alignment Prompting for Unlearning in LLMs
Research on unlearning sensitive information from LLMs via controllable alignment prompting without modifying weights, addressing regulatory compliance.
5/18/2026
Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction
Benchmark comparing model scaling effects across 26 molecular property prediction tasks, finding compact and task-specific models often outperform large foundation models.
5/18/2026
Gradient-Discrepancy Acquisition for Pool-Based Active Learning
Gradient-based acquisition criterion for pool-based active learning derived from generalization bounds.
5/18/2026
MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
Multi-scale MLP architecture for long-term time series forecasting capturing patterns at multiple temporal resolutions.
5/18/2026
MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving
System for serving mixture-of-experts LLMs on prefill-only workloads without redundant distributed execution overhead.
5/18/2026
The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
Investigation of why transformers fail at counting tasks and demonstration that failures stem from output representation rather than internal counting inability.
5/18/2026
PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics
Physics-embedded rectified flow generative model for reconstructing PDE-governed spatiotemporal fields with uncertainty quantification from sparse measurements.
5/18/2026
Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs
Active learning acquisition rule using pretrained MLIP latent representations to reduce quantum chemical labeling costs in molecular potential training.
5/18/2026
Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies
State vector space partitioning method to distill black-box RL policies into interpretable linear subpolicies using support vector machines.
5/18/2026
Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
Pass-rate control method for binary-reward RL in software engineering tasks, steering trajectories toward maximally informative regimes for policy optimization.
5/18/2026
Estimating the expected output of wide random MLPs more efficiently than sampling
Technique for estimating expected output of wide random MLPs at initialization without sampling, using activation distribution approximations.
5/18/2026
Information-Preserving Domain Transfer with Unlabeled Data in Misspecified Simulation-Based Inference
Domain transfer method for simulation-based inference under model misspecification using unlabeled real-world data.
5/18/2026
Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning
Universal semi-supervised learning framework handling arbitrary unlabeled data distributions using simplex anchored structural inference.
5/18/2026
The Geometric Structure of Models Learning Sparse Data
Theoretical analysis of how models learn sparse data regimes where the manifold hypothesis does not apply.
5/18/2026
PRIM: Meta-Learned Bayesian Root Cause Analysis
Meta-learning approach framing root cause analysis in complex systems as Bayesian inference over synthetic causal model priors.
5/18/2026
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
Technique using spectral orthogonal gradient projection to address catastrophic forgetting in LLM continual learning through orthogonal parameter updates.
5/18/2026
Accelerating Zeroth-Order Spectral Optimization with Partial Orthogonalization from Power Iteration
Method for accelerating zeroth-order optimization in LLM fine-tuning via partial orthogonalization, enabling efficient adaptation on edge devices without backpropagation.
5/18/2026
Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers
Research on how FFN architecture choices in Transformers affect attention mechanisms, comparing dense, gated, and sparse mixture-of-experts designs on algorithmic tasks.
5/18/2026
Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
Key-Value Means introduces block-recurrent attention with expandable compressed memory for O(N) transformers with long-context capability.
5/18/2026
The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies
Reveals format confound in chain-of-thought corruption studies where answer placement rather than computation determines faithfulness.
5/18/2026
Likelihood scoring for continuations of mathematical text: a self-supervised benchmark with tests for shortcut vulnerabilities
Self-supervised benchmark for evaluating LLM continuation prediction on hidden mathematical text with shortcut vulnerability tests.
5/18/2026
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Four-stage post-training workflow for LLM reasoning combining sparse-reward RL, KL warmup, and distillation for effective data allocation.
5/18/2026
ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization
ODRPO decomposes discrete rewards for robust LLM alignment via RLAIF, addressing stochasticity in LLM-based auto-raters.
5/18/2026
Scaling Laws for Mixture Pretraining Under Data Constraints
Studies optimal mixture ratios of scarce target data with abundant generic data during LLM pre-training under data constraints.
5/18/2026
Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
Active learning framework for machine-learning interatomic potentials using neural tangent kernels with force-aware acquisition.
5/18/2026
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
Applies sparse autoencoders to extract interpretable features from EEG foundation models for clinical applications.
5/18/2026
Active Learners as Efficient PRP Rerankers
Uses active learning to efficiently rerank LLM pairwise preference judgments, treating it as robust top-K recovery rather than sorting.