4/8/2026
The Planetary Cost of AI Acceleration, Part II: The 10th Planetary Boundary and the 6.5-Year Countdown
Opinion piece on environmental and computational costs of scaling LLM agents and implications for planetary boundaries.
4/8/2026
Self-Supervised Foundation Model for Calcium-imaging Population Dynamics
Self-supervised foundation model (CalM) trained on neuronal calcium traces for neuroscience task transfer learning.
4/8/2026
MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
Proposes MG²-RAG, a multi-granularity graph approach for retrieval-augmented generation in multimodal LLMs to improve cross-modal reasoning without costly text translation.
4/8/2026
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
Independent evaluation of Claude Code's auto mode permission system for AI coding agents, testing security gates on ambiguous authorization scenarios.
4/8/2026
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Introduces Squeez, a method for pruning tool outputs in coding agents by identifying minimal relevant evidence blocks. Includes 11,477-example benchmark from SWE-bench.
4/8/2026
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
CURE enables privacy-preserving unlearning in LLM-based recommendation systems using circuit-aware techniques for removing user data.
4/8/2026
Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
Cactus improves speculative sampling for LLM decoding by relaxing strict distribution matching to allow acceptable variations like top-k sampling.
4/8/2026
Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression
Prune-Quantize-Distill pipeline for neural network compression optimizing wall-clock inference time rather than parameter count or FLOPs.
4/8/2026
Architecture Without Architects: How AI Coding Agents Shape Software Architecture
Analysis of implicit architectural decisions made by AI coding agents, identifying five mechanisms and six prompt-architecture coupling patterns.
4/8/2026
FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
FreakOut-LLM framework investigates whether emotionally charged prompts compromise safety alignment in ten LLMs using psychological stimuli.
4/8/2026
Evaluation of Embedding-Based and Generative Methods for LLM-Driven Document Classification: Opportunities and Challenges
Comparative evaluation of embedding-based and generative models for document classification, showing Vision-Language Models with CoT achieve 82% zero-shot accuracy.
4/8/2026
PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities
PRIME enables multimodal self-supervised pretraining for cancer prognosis with missing modalities by combining histopathology, gene expression, and reports.
4/8/2026
Closed-Loop Autonomous Software Development via Jira-Integrated Backlog Orchestration: A Case Study in Deterministic Control and Safety-Constrained Automation
Case study of closed-loop software development system managing backlog via deterministic pipeline with Jira integration and safety constraints.
4/8/2026
Learning Stable Predictors from Weak Supervision under Distribution Shift
Studies learning from weak supervision under distribution shift in CRISPR-Cas13d experiments where guidance efficacy is indirectly inferred.
4/8/2026
EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content
EduIllustrate benchmark evaluates LLMs on generating multimodal educational content combining accurate diagrams with step-by-step explanations.
4/8/2026
Generalizable Audio-Visual Navigation via Binaural Difference Attention and Action Transition Prediction
BDATP framework for audio-visual navigation using binaural attention and action prediction to improve generalization in unseen 3D environments.
4/8/2026
YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks
YMIR dataset and CNN model for classifying five Yemeni music genres, addressing underrepresentation of non-Western music in MIR research.
4/8/2026
Comparative Characterization of KV Cache Management Strategies for LLM Inference
Comparative analysis of key-value cache management strategies for efficient LLM inference under different model sizes and context lengths.
4/8/2026
Scaling Coding Agents via Atomic Skills
Proposes training LLM coding agents on five atomic coding skills (localization, editing, testing, reproduction, review) for improved generalization.
4/8/2026
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
StarVLA provides a modular open-source codebase for building vision-language-action embodied agents with standardized evaluation protocols.
4/8/2026
Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space
Phase-Associative Memory is a recurrent sequence model using complex-valued representations achieving competitive perplexity on WikiText-103.
4/8/2026
ID-Sim: An Identity-Focused Similarity Metric
ID-Sim proposes an identity-focused similarity metric for vision models to improve evaluation of personalized image generation tasks.
4/8/2026
PCA-Driven Adaptive Sensor Triage for Edge AI Inference
PCA-Triage is a streaming algorithm for adaptive sensor sampling in IoT networks using principal component analysis to manage bandwidth constraints.
4/8/2026
This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA
Study evaluating LLM sensitivity to prompt phrasing in medical question answering, showing inconsistent responses despite identical underlying evidence.
4/8/2026
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
DynLMC generates synthetic multivariate time series with time-varying correlations and cross-channel dependencies for training foundation models.
4/8/2026
AutoLALA: Automatic Loop Algebraic Locality Analysis for AI and HPC Kernels
arXiv paper presenting AutoLALA, open-source tool analyzing data locality in loop programs for HPC and AI workloads.
4/8/2026
Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
arXiv paper on privacy-preserving graph learning for additive manufacturing sensor data using differential privacy techniques.
4/8/2026
Nidus: Externalized Reasoning for AI-Assisted Engineering
arXiv paper on Nidus, a governance runtime using Claude, Gemini, Codex to mechanize V-model for AI-assisted software delivery.
4/8/2026
Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation
arXiv paper proposing OmniScore, deterministic evaluation metrics for multilingual text generation as alternative to LLM judges.
4/8/2026
Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks
arXiv paper auditing code-editing benchmarks for LLMs, finding flaws in existing evaluation methods for instructed code modification.
4/8/2026
Simultaneous Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models
arXiv paper on diffusion models for medical imaging, generating paired mammogram views for cancer screening datasets.
4/8/2026
Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
arXiv paper on Decision Pre-Trained Transformer for in-context reinforcement learning, enabling scalable generalist agent training.
4/8/2026
CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation
arXiv paper on CRAB method for mitigating popularity bias in generative recommendation systems via codebook rebalancing.
4/8/2026
$\pi^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models
arXiv paper presenting π² pipeline for curating reasoning data from structured sources to improve LLM long-context reasoning.
4/8/2026
Watch Before You Answer: Learning from Visually Grounded Post-Training
arXiv paper on vision-language models learning from grounded video data, finding text-only bias in video benchmarks.
4/8/2026
Offline RL for Adaptive Policy Retrieval in Prior Authorization
arXiv paper modeling prior authorization policy retrieval as MDP for adaptive decision-making in healthcare insurance.
4/8/2026
Reasoning Through Chess: How Reasoning Evolves from Data Through Fine-Tuning and Reinforcement Learning
arXiv paper on how reasoning evolves in language models through fine-tuning and RL, studied via chess task performance.
4/8/2026
EffiPair: Improving the Efficiency of LLM-generated Code with Relative Contrastive Feedback
EffiPair: Relative Contrastive Feedback method for improving runtime and memory efficiency of LLM-generated code without model fine-tuning.
4/8/2026
Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
Compiled AI: Paradigm where LLMs generate executable code during compilation for deterministic, model-free workflow automation execution.
4/8/2026
Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
Planning to Explore: Curiosity-driven planning approach for LLM-based test generation using Bayesian principles to reach deep code branches.
4/8/2026
What Makes a Good Response? An Empirical Analysis of Quality in Qualitative Interviews
Analysis of 10 proposed measures for evaluating qualitative interview response quality to determine predictive validity.
4/8/2026
Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning
Adaptive Thinking Budgets: Method for allocating inference-time compute efficiently across multi-turn LLM reasoning based on turn difficulty.
4/8/2026
Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI
Modality-aware vector-quantized VAE for reconstructing multimodal brain MRI data across different imaging modalities.
4/8/2026
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
Large Sparse Reconstruction Model studies scaling transformer context windows for improved 3D object reconstruction from multiple views.
4/8/2026
OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
OrthoFuse: Training-free method for merging multiple adapters in diffusion models using Riemannian geometry.
4/8/2026
Improving Clinical Trial Recruitment using Clinical Narratives and Large Language Models
Study comparing encoder and decoder-based LLMs for screening clinical narratives to automate patient recruitment for clinical trials.
4/8/2026
RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains
RoboPlayground: Framework for democratizing robotic manipulation evaluation through structured physical domain benchmarks.
4/8/2026
Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
Optimization strategies using curvature-aware methods to improve convergence speed and accuracy of physics-informed neural networks.
4/8/2026
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
XMark: Multi-bit watermarking method for embedding imperceptible messages in LLM-generated text for attribution and tracing.
4/8/2026
Exemplar Retrieval Without Overhypothesis Induction: Limits of Distributional Sequence Learning in Early Word Learning
Study on how transformer language models learn second-order generalizations about object categories from synthetic data.