4/13/2026
AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning
AdaCubic optimizer using adaptive cubic regularization with Hutchinson's method for approximating Hessian in deep learning.
4/13/2026
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
One-step diffusion model for efficient chest X-ray report generation reducing inference latency compared to autoregressive models.
4/13/2026
SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
Method for safely updating deep reinforcement learning policies while preserving safety guarantees on previously encountered tasks.
4/13/2026
Integrated electro-optic attention nonlinearities for transformers
Hardware optimization using electro-optic nonlinearities to replace softmax bottleneck in transformer attention mechanisms.
4/13/2026
Event-Driven Temporal Graph Networks for Asynchronous Multi-Agent Cyber Defense in NetForge_RL
High-fidelity cyber operations simulator (NetForge_RL) using temporal graph networks for multi-agent reinforcement learning in cybersecurity.
4/13/2026
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
OmniBehavior benchmark for evaluating LLMs as user simulators on long-horizon, cross-scenario behavior traces from real-world data.
4/13/2026
Self-Sovereign Agent
Investigation of self-sovereign AI agents that can economically sustain themselves without human involvement using LLMs and agent frameworks.
4/13/2026
A Representation-Level Assessment of Bias Mitigation in Foundation Models
Analysis of how bias mitigation reshapes embedding spaces in BERT and Llama2 through representational analysis of gender-occupation associations.
4/13/2026
Temperature-Dependent Performance of Prompting Strategies in Extended Reasoning Large Language Models
Systematic evaluation of chain-of-thought vs zero-shot prompting across temperature settings using Grok-4.1 for extended reasoning LLMs.
4/13/2026
Attention-Based Sampler for Diffusion Language Models
Research on attention-based sampling for diffusion language models enabling parallel decoding instead of sequential auto-regressive approach.
4/13/2026
Dynamic sparsity in tree-structured feed-forward layers at scale
Tree-structured sparse feed-forward layers as drop-in MLP replacements in transformers enabling conditional computation via routing.
4/13/2026
Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control
Theoretical framework for reward fine-tuning of diffusion models using stochastic optimal control and adjoint matching.
4/13/2026
OpenKedge: Governing Agentic Mutation with Execution-Bound Safety and Evidence Chains
Protocol governing autonomous agent mutations with execution-bound safety checks and evidence chains for API-centric architectures.
4/13/2026
TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening
Open-source browser extension for AI-assisted title and abstract screening in literature review with no-code, serverless architecture.
4/13/2026
Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines
Attack method on LLM orchestration systems where single requests decompose into benign subtasks that jointly violate security policies.
4/13/2026
Sustained Impact of Agentic Personalisation in Marketing: A Longitudinal Case Study
Longitudinal case study of autonomous personalization systems in CRM with human-in-the-loop oversight requirements.
4/13/2026
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
Method to reduce hallucinations in 3D embodied AI agents using visual contrastive decoding on multimodal LLMs.
4/13/2026
Unified Multimodal Uncertain Inference
Multimodal inference task with text, audio, video for producing calibrated probability estimates of hypotheses with fine-grained uncertainty.
4/13/2026
Toward Hardware-Agnostic Quadrupedal World Models via Morphology Conditioning
Hardware-agnostic world models for quadrupedal robots using morphology conditioning to generalize across different robot embodiments.
4/13/2026
StaRPO: Stability-Augmented Reinforcement Policy Optimization
RL framework for improving LLM reasoning by optimizing for logical consistency and structural integrity of reasoning processes, not just final answers.
4/13/2026
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Proposes utility-centric approach to information retrieval for RAG systems, optimizing retrieved documents for task completion rather than topical relevance.
4/13/2026
Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift
Supervised adaptation of vision-language models outperforms prompting for cloud segmentation in remote sensing under domain shift.
4/13/2026
ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
ASTRA: Adaptive semantic tree reasoning architecture for table question answering using LLMs with improved serialization and schema flexibility.
4/13/2026
Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
Regime-conditional retrieval approach with transferable router for two-hop QA using surface-text predicates for routing decisions.
4/13/2026
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
ImageProtector method prevents multi-modal LLMs from analyzing images via visual prompt injection for privacy protection.
4/13/2026
Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks
Multi-agent mixture of experts with plasticity enhancement for UAV communication networks under non-stationary conditions using deep RL.
4/13/2026
Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments
Continual visual place recognition system for aerial autonomy addressing catastrophic forgetting using geometric memory management in dynamic environments.
4/13/2026
NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System
NyayaMind framework for transparent legal judgment prediction in Indian courts using structured reasoning aligned with legal methodology.
4/13/2026
CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
CLIP-Inspector framework for detecting backdoor attacks in prompt-tuned CLIP models via out-of-distribution trigger inversion.
4/13/2026
Detecting Diffusion-generated Images via Dynamic Assembly ForestsDetecting Diffusion-generated Images via Dynamic Assembly Forests
Dynamic Assembly Forest model detecting diffusion-generated images using ensemble methods, alternative to deep neural network approaches.
4/13/2026
FIRE-CIR: Fine-grained Reasoning for Composed Fashion Image Retrieval
FIRE-CIR framework for composed image retrieval using vision-language models with fine-grained reasoning about what to preserve and modify.
4/13/2026
MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs
MATCHA: DNN deployment framework generating concurrent schedules for heterogeneous multi-accelerator edge SoCs using constraint programming optimization.
4/13/2026
Identifying Causal Effects Using a Single Proxy Variable
Theoretical framework for identifying causal effects using single proxy variables of unobserved confounders under completeness assumptions.
4/13/2026
MixFlow: Mixed Source Distributions Improve Rectified Flows
MixFlow method improving diffusion models by using mixed source distributions instead of standard Gaussian to reduce generative path curvature.
4/13/2026
Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies
Symbolic-Neural Consistency Audit (SNCA) framework that extracts LLM self-stated safety policies via prompts and verifies model adherence to them.
4/13/2026
Natural Riemannian gradient for learning functional tensor networks
Riemannian gradient descent approach for optimizing low-rank functional tensor networks on arbitrary loss functions beyond least-squares regression.
4/13/2026
Online Intention Prediction via Control-Informed Learning
Online intention prediction framework for autonomous systems using inverse reinforcement learning with time-varying objectives and unknown parameters.
4/13/2026
Iterative Identification Closure: Amplifying Causal Identifiability in Linear SEMs
Iterative Identification Closure framework for determining causal identifiability in linear structural equation models with latent confounders.
4/13/2026
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
Fragment-based graph neural network integrated with many-body expansion theory for predicting potential energy surfaces in chemical systems.
4/13/2026
Biologically-Grounded Multi-Encoder Architectures as Developability Oracles for Antibody Design
CrossAbSense framework using protein language model encoders and attention decoders to predict antibody properties for therapeutic design validation.
4/13/2026
Variational Quantum Physics-Informed Neural Networks for Hydrological PDE-Constrained Learning with Inherent Uncertainty Quantification
Hybrid quantum-classical physics-informed neural networks for hydrological modeling with uncertainty quantification using variational quantum circuits.
4/13/2026
Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
Theoretical analysis of loss landscape in two-layer ReLU neural networks, characterizing local minima and their connection to stochastic gradient descent dynamics.
4/13/2026
Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
Learning-to-Defer framework that routes inputs to experts while selecting additional information (retrieved documents, tool outputs) to provide each expert, extending traditional routing systems.
4/13/2026
Automated Instruction Revision (AIR): A Structured Comparison of Task Adaptation Strategies for LLM
Systematic comparison of LLM task adaptation strategies including instruction revision, prompt optimization, and retrieval methods.
4/13/2026
RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
Post-training method enabling LLMs to retrieve and reason over long-context information effectively.
4/13/2026
Envisioning the Future, One Step at a Time
Video prediction model representing scene dynamics as sparse point trajectories for efficient future frame synthesis.
4/13/2026
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Framework for training LLMs to make evidence-dependent predictions by grounding supervision in case-specific evidence.
4/13/2026
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism
Mechanistic study using weight pruning to identify unified internal mechanism LLMs use for generating harmful content.
4/13/2026
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Method using low-rank techniques for Bayesian uncertainty quantification in neural networks via Laplace approximation.
4/13/2026
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
Research on polysemanticity in LLMs showing neurons encode multiple concepts, challenging discrete attribution methods for model interpretability.