2/17/2026
Algebraic Quantum Intelligence: A New Framework for Reproducible Machine Creativity
Algebraic quantum intelligence framework proposing quantum computing approach to improve creative output generation in LLMs.
2/17/2026
DenseMLLM: Standard Multimodal LLMs are Intrinsic Dense Predictors
DenseMLLM: framework enabling multimodal LLMs for dense prediction tasks like segmentation and depth estimation without task-specific decoders.
2/17/2026
When Test-Time Guidance Is Enough: Fast Image and Video Editing with Diffusion Guidance
Fast image and video editing using diffusion model guidance without costly vector-Jacobian product computations.
2/17/2026
CORPGEN: Simulating Corporate Environments with Autonomous Digital Employees in Multi-Horizon Task Environments
CORPGEN: multi-horizon task environment benchmark for evaluating autonomous agents on concurrent long-horizon tasks with dependencies and reprioritization.
2/17/2026
Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models
Sali-Cache: dual-signal KV-cache optimization framework for efficient long-form video understanding in vision-language models.
2/17/2026
Federated Ensemble Learning with Progressive Model Personalization
Federated ensemble learning approach with progressive personalization addressing statistical heterogeneity across distributed clients.
2/17/2026
GRAIL: Goal Recognition Alignment through Imitation Learning
GRAIL: imitation learning approach for goal recognition alignment enabling accurate identification of agent goals from behavior for AI alignment.
2/17/2026
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
AD-Bench: real-world benchmark for evaluating LLM agents on complex advertising and marketing analytics tasks requiring multi-round reasoning.
2/17/2026
STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts
STATe-of-Thoughts: interpretable inference-time compute method using structured action templates for improved diversity and explainability in LLM reasoning.
2/17/2026
Fast Compute for ML Optimization
SM-EM algorithm for ML optimization reformulating EM iterations as weighted least squares with learnable scaling analogous to Adam optimizer components.
2/17/2026
FMMD: A multimodal open peer review dataset based on F1000Research
FMMD: Multimodal peer review dataset from F1000Research for training AI systems for automated scholarly paper evaluation.
2/17/2026
Floe: Federated Specialization for Real-Time LLM-SLM Inference
Floe: Federated learning framework combining cloud LLMs with edge small language models for low-latency, privacy-preserving real-time inference.
2/17/2026
Benchmarking at the Edge of Comprehension
Analysis of LLM benchmark saturation problem: frontier models exhaust new benchmarks quickly, threatening ability to measure AI progress.
2/17/2026
Offline Learning of Nash Stable Coalition Structures with Possibly Overlapping Coalitions
Coalition formation model for selfish agents with possibly overlapping coalitions under partial information using offline learning.
2/17/2026
AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation
AdaptManip: Reinforcement learning framework for humanoid robots to autonomously perform navigation, object lifting, and delivery without demonstrations.
2/17/2026
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
InnoEval: Framework for evaluating AI research ideas using LLMs with knowledge-grounded, multi-perspective reasoning and collective deliberation.
2/17/2026
LRD-MPC: Efficient MPC Inference through Low-rank Decomposition
LRD-MPC uses low-rank decomposition to improve efficiency of secure multi-party computation for machine learning inference.
2/17/2026
Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces
PITA dataset with 23M propositional logic statements examining how reasoning traces support LLM reasoning and length generalization limits.
2/17/2026
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Frontier AI Risk Management Framework analyzing risks from rapidly advancing AI models and agentic AI systems, version 1.5 technical report.
2/17/2026
Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems
SWA: Game-theoretic framework for multi-agent LLM systems balancing individual alignment with collective stability through modified inference-time decisions.
2/17/2026
Learning Transferability: A Two-Stage Reinforcement Learning Approach for Enhancing Quadruped Robots' Performance in U-Shaped Stair Climbing
Two-stage deep reinforcement learning approach for training quadruped robots to climb U-shaped stairs autonomously.
2/17/2026
Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC
COOL-MC framework for formally verifying and explaining reinforcement learning policies for sepsis treatment using model checking.
2/17/2026
Beyond Translation: Evaluating Mathematical Reasoning Capabilities of LLMs in Sinhala and Tamil
Evaluates mathematical reasoning capabilities of LLMs in Sinhala and Tamil languages versus English-like translation representations.
2/17/2026
TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrations
TWISTED-RL framework for robotic knot-tying using hierarchical reinforcement learning agents without human demonstrations.
2/17/2026
MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs
MATEO: multimodal benchmark for evaluating LVLMs on temporal reasoning and planning with directed acyclic graph task execution orders.
2/17/2026
LongAudio-RAG: Event-Grounded Question Answering over Multi-Hour Long Audio
LongAudio-RAG: hybrid framework combining audio-language models with retrieval-augmented generation for multi-hour audio question answering.
2/17/2026
VariViT: A Vision Transformer for Variable Image Sizes
VariViT: Vision Transformer architecture supporting variable image sizes without fixed-size patches, addressing medical imaging challenges.
2/17/2026
Tabular Foundation Models Can Learn Association Rules
Tabular foundation models applied to association rule mining, outperforming classical and neural approaches especially in low-data regimes.
2/17/2026
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Analysis of prefill attack vulnerability in open-weight LLMs, exposing systematic security risks in models relying on internal safeguards.
2/17/2026
Evolutionary System Prompt Learning can Facilitate Reinforcement Learning for LLMs
Evolutionary System Prompt Learning (E-SPL) method for jointly improving LLM contexts and weights through reinforcement learning iterations.
2/17/2026
LLMStructBench: Benchmarking Large Language Model Structured Data Extraction
LLMStructBench: benchmark for evaluating LLMs on structured data extraction and JSON generation from natural language across 22 models and 5 prompting strategies.
2/17/2026
Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
Research on behavioral self-awareness in LLMs fine-tuned with incorrect data, examining how misalignment emerges and shifts with realignment.
2/17/2026
Return of the Schema: Building Complete Datasets for Machine Learning and Reasoning on Knowledge Graphs
Dataset paper on knowledge graph refinement algorithms with schema-level information and neurosymbolic techniques for ontological reasoning.
2/17/2026
Exploring the limits of pre-trained embeddings in machine-guided protein design: a case study on predicting AAV vector viability
Study on pre-trained protein sequence embeddings for machine-learning-based protein design, addressing challenges with sparse mutation datasets in bioengineering.
2/17/2026
RF-GPT: Teaching AI to See the Wireless World
RF-GPT extends LLMs and multimodal models to natively support radio-frequency signals for wireless systems, bridging gap between LLM-based telecom approaches and RF signal processing.
2/17/2026
Multi-dimensional Persistent Sheaf Laplacians for Image Analysis
Multi-dimensional persistent sheaf Laplacian framework for image analysis addressing dimensionality reduction sensitivity.
2/17/2026
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
Theoretical analysis of temperature scaling properties for classifier calibration and LLM stochasticity control.
2/17/2026
Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
Drift-diffusion matching framework embedding asymmetric RNN dynamics in latent manifolds for biological neural computation.
2/17/2026
Activation-Space Uncertainty Quantification for Pretrained Networks
GAPA: post-hoc Gaussian Process method for uncertainty quantification in pretrained networks via activation-space modeling.
2/17/2026
ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery
ThermEval benchmark for evaluating vision-language model generalization on thermal imagery across surveillance and medical applications.
2/17/2026
Distributed Quantum Gaussian Processes for Multi-Agent Systems
Quantum-enhanced Gaussian processes with distributed training for multi-agent systems using quantum kernel embeddings.
2/17/2026
BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames
BPP method for robot imitation learning attending to relevant historical frames via key frame selection in long-context tasks.
2/17/2026
Cold-Start Personalization via Training-Free Priors from Structured World Models
Cold-start personalization using structured world models and RL for efficient user preference inference with limited interaction budget.
2/17/2026
Learning with Subset Stacking
Regression algorithm using subset stacking for heterogeneous data with local predictors trained on random input-space subsets.
2/17/2026
When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
Analysis of sample efficiency in offline policy selection for reinforcement learning via off-policy evaluation and Bellman error.
2/17/2026
Permutation-based Inference for Variational Learning of Directed Acyclic Graphs
PIVID method for inferring Bayesian network structure from observational data using permutation-based variational inference.
2/17/2026
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
Memory-efficient zeroth-order optimizer (MeZO) for LLM fine-tuning using only forward passes, with sparse parameter improvements.
2/17/2026
Optimal Design for Human Preference Elicitation
Optimal design methods for efficient human preference elicitation to reduce annotation costs in preference learning models.
2/17/2026
Synergizing Foundation Models and Federated Learning: A Survey
Survey of federated learning combined with foundation models for privacy-preserving distributed training.
2/17/2026
GraphFM: A generalist graph transformer that learns transferable representations across diverse domains
Multi-graph pretraining approach enabling graph transformers to learn transferable representations across diverse domains.