2/17/2026
Residual Feature Integration is Sufficient to Prevent Negative Transfer
ML research on preventing negative transfer in transfer learning through residual feature integration.
2/17/2026
Advancing Software Quality: A Standards-Focused Review of LLM-Based Assurance Techniques
Survey of LLM-based techniques for software quality assurance, covering requirement analysis, code review, and test generation automation.
2/17/2026
MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
MoESD demonstrates speculative decoding effectiveness for accelerating sparse Mixture of Experts LLM inference without accuracy loss.
2/17/2026
KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider
Characterization of KV cache behavior in large-scale LLM serving with analysis of cache eviction policies and workload-dependent optimization.
2/17/2026
High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
HALT method for post-training LLMs to abstain on tasks outside their capability, reducing hallucination through capability-aligned fine-tuning.
2/17/2026
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
Techniques for improving data efficiency in LLM RL fine-tuning using difficulty-targeted online selection and rollout replay.
2/17/2026
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
RuleReasoner method combining RL with domain-aware sampling for robust rule-based reasoning across varying rule formats and complexity.
2/17/2026
Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization
SVD-based quantization method for compressing delta parameters from LLM fine-tuning with analysis of underlying compression mechanisms.
2/17/2026
Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis
Survey of foundation models for autonomous driving focusing on scenario generation and analysis for simulation-based testing.
2/17/2026
HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
HYPER foundation model for inductive link prediction with knowledge hypergraphs, generalizing to novel entities and relation types.
2/17/2026
NeuronSeek: On Stability and Expressivity of Task-driven Neurons
NeuronSeek framework using symbolic regression to discover and construct neural networks with optimized task-driven neurons.
2/17/2026
An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
DeepRare multi-agent system using LLMs with traceable reasoning for differential diagnosis of rare diseases through agentic workflow.
2/17/2026
Chain of Thought in Order: Discovering Learning-Friendly Orders for Arithmetic
Study on optimal ordering of chain-of-thought reasoning steps in Transformers for mathematical tasks, showing significant impact on reasoning difficulty.
2/17/2026
wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
Weighted policy optimization method for improving reasoning in diffusion-based LLMs through RL without requiring exact likelihood computations.
2/17/2026
A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
DeepRobot system uses LLMs for robotic task planning with verbal RL feedback loop to align models with real-world robot embodiment and constraints.
2/17/2026
Virne: A Comprehensive Benchmark for RL-based Network Resource Allocation in NFV
Virne benchmark framework for evaluating deep RL methods on network resource allocation in Network Function Virtualization infrastructure.
2/17/2026
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
GEPA uses genetic algorithms and Pareto optimization for prompt evolution as alternative to RL fine-tuning of LLMs, achieving better performance with fewer rollouts.
2/17/2026
FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
FGBench dataset and benchmark for evaluating LLM reasoning on molecular property prediction at functional group level with structure-aware interpretability.
2/17/2026
Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
Research investigating unintended deception in LLMs on benign prompts without explicit hidden objectives, revealing trustworthiness risks in reasoning tasks.
2/17/2026
Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
Diagnostic framework for evaluating synthetic dialogue generation for contact centers using structured supervision on call attributes.
2/17/2026
Towards Production-Worthy Simulation for Autonomous Cyber Operations
Framework extending CybORG environment for training RL agents in autonomous cyber operations with production-worthy simulation accuracy.
2/17/2026
A Financial Brain Scan of the LLM
Interpretability study brain-scanning LLMs to identify economic concepts guiding financial forecasts and map relative importance without performance reduction.
2/17/2026
ART: Adaptive Resampling-based Training for Imbalanced Classification
Adaptive Resampling-based Training method dynamically adjusts training data distribution based on per-class learning difficulty for imbalanced classification.
2/17/2026
Large Language Model Integration with Reinforcement Learning to Augment Decision-Making in Autonomous Cyber Operations
Integration of LLMs with RL for autonomous cyber operations, using LLM pre-trained knowledge to augment agent decision-making and reduce exploration cost.
2/17/2026
Reinforcement Learning-Based Market Making as a Stochastic Control on Non-Stationary Limit Order Book Dynamics
RL-based market making strategy modeling limit order book dynamics as stochastic control problem for algorithmic trading.
2/17/2026
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
DiffusionNFT introduces online reinforcement learning for diffusion models using forward process, addressing limitations in post-training diffusion model optimization.
2/17/2026
Evolution of Concepts in Language Model Pre-Training
Interpretability research tracking feature evolution during language model pre-training using sparse dictionary learning (crosscoders) to understand capability emergence.
2/17/2026
Through the Lens of Human-Human Collaboration: A Configurable Research Platform for Exploring Human-Agent Collaboration
Research platform for exploring human-agent collaboration using LLM agents, applying principles from human-mediated computer collaboration to human-LLM partnerships.
2/17/2026
AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field
AECBench benchmark evaluates LLM robustness and reliability in Architecture, Engineering, and Construction domain with hierarchical knowledge evaluation.
2/17/2026
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Research showing activation steering technique for controlling LLM behavior systematically breaks model alignment safeguards and makes models comply with harmful requests.
2/17/2026
ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
ArXiv paper proposing ReliabilityRAG, provably robust defense against prompt injection and retrieval corpus attacks on RAG-based web search systems.
2/17/2026
LLM DNA: Tracing Model Evolution via Functional Representations
ArXiv paper introducing LLM DNA method for tracing evolutionary relationships between models via functional representations without task-specific constraints.
2/17/2026
VoiceBridge: General Speech Restoration with One-step Latent Bridge Models
ArXiv paper proposing VoiceBridge, one-step latent bridge model for general speech restoration from diverse distortions at 48 kHz fullband quality.
2/17/2026
BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
ArXiv paper introducing BiasFreeBench, standardized benchmark for evaluating and comparing bias mitigation methods in LLM responses with consistent metrics.
2/17/2026
Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
ArXiv paper introducing EAPrivacy benchmark for measuring physical-world privacy awareness of LLM-powered embodied agents in procedurally generated scenarios.
2/17/2026
Where to Add PDE Diffusion in Transformers
ArXiv paper studying optimal placement of PDE diffusion layers in hybrid transformer architectures to add local geometric priors along sequence axis.
2/17/2026
RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
ArXiv paper proposing RACE Attention, a strictly linear-time attention mechanism enabling long-sequence training beyond quadratic softmax attention limitations.
2/17/2026
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
ArXiv paper introducing SECA, method for eliciting LLM hallucinations using semantically equivalent and coherent adversarial attacks to test reliability.
2/17/2026
Inverse Mixed-Integer Programming: Learning Constraints then Objective Functions
ArXiv paper addressing data-driven inverse optimization for mixed-integer linear programs by learning both constraints and objective functions from observed decisions.
2/17/2026
The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach
ArXiv paper comparing context management strategies for end-to-end spoken dialogue state tracking using Speech-LLMs on SpokenWOZ corpus.
2/17/2026
Discrete State Diffusion Models: A Sample Complexity Perspective
ArXiv paper providing theoretical analysis of sample complexity in discrete-state diffusion models for text, sequences, and combinatorial structures.
2/17/2026
Challenges and Requirements for Benchmarking Time Series Foundation Models
ArXiv paper examining benchmarking challenges for Time Series Foundation Models, addressing test set integrity issues as training corpora grow large.
2/17/2026
Algorithmic Primitives and Compositional Geometry of Reasoning in Language Models
ArXiv paper introducing framework for tracing and steering algorithmic primitives underlying LLM multi-step reasoning by linking reasoning traces to internal activations.
2/17/2026
Learning under Quantization for High-Dimensional Linear Regression
ArXiv paper providing first theoretical analysis of low-bit quantization effects on learning performance in high-dimensional linear regression settings.
2/17/2026
Top-Down Semantic Refinement for Image Captioning
ArXiv paper proposing top-down semantic refinement technique for improving image captioning quality in Vision-Language Models through multi-step generation.
2/17/2026
Batch Speculative Decoding Done Right
ArXiv paper identifying critical correctness violations in existing batch speculative decoding implementations and proposing fixes to ensure output equivalence with standard autoregressive generation.
2/17/2026
AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence
ArXiv paper introducing AthenaBench, a benchmark for evaluating LLMs on cyber threat intelligence tasks including analysis of unstructured security reports.
2/17/2026
Importance Ranking in Complex Networks via Influence-aware Causal Node Embedding
Influence-aware causal node embedding method for quantifying node importance in complex networks, applicable to influence maximization and network analysis.
2/17/2026
On the Mechanisms of Collaborative Learning in VAE Recommenders
Theoretical analysis of collaborative learning in VAE-based recommender systems, showing latent proximity governs how binary masking improves performance.
2/17/2026
Formal Reasoning About Confidence and Automated Verification of Neural Networks
Framework for formally reasoning about confidence and robustness in neural networks, generalizing existing adversarial robustness verification approaches.