Highlights
Top disruptiveness scores across every published week. Prefer the free explainer when one exists.
#1 · score 93 · 2026-W41
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evalua…
Read free explainer →
#2 · score 93 · 2026-W34
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundat…
Read free explainer →
#3 · score 93 · 2026-W35
AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement.…
Read free explainer →
#4 · score 93 · 2026-W36
Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation
Anatomically plausible segmentation remains challenging because of low contrast, ambiguous boundaries, and modality-specific artifacts. Interactive segmentatio…
Read free explainer →
#5 · score 93 · 2026-W37
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as su…
Read free explainer →
#6 · score 93 · 2026-W38
Rapid Learning of Dexterous In-Hand Pen Writing through Real-Time Jacobian Estimation
Dexterous in-hand manipulation of a grasped object with an anthropomorphic hand is an unsolved frontier for robot dexterity. The contact-richness and highly dy…
Read free explainer →
#7 · score 93 · 2026-W39
Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control
World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the policy to…
Read free explainer →
#8 · score 93 · 2026-W40
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy g…
Read free explainer →
#9 · score 92 · 2026-W41
Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
The emergence of foundation models for molecular property prediction requires a high degree of AI data readiness, including reliable metadata annotation. Howev…
Read free explainer →
#10 · score 91 · 2026-W38
MindTopo: Can Foundation Models Reason in Topological Space?
Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under conti…
Read free explainer →
#11 · score 91 · 2026-W39
HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition
More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet diagnosis remains difficult because patients initially presen…
Read free explainer →
#12 · score 90 · 2026-W40
Quantum Feature Selection for Biomedical Data Analysis
Feature selection is an essential step for reducing complexity of high dimensional data, usually in preparation for developing machine learning models such as…
Read free explainer →
#13 · score 89 · 2026-W41
InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation
We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills, improvin…
Read free explainer →
#14 · score 89 · 2026-W34
MKG-CARE: Case-Aware Reasoning with Multimodal Knowledge Graphs for Explainable Medical Image Diagnosis
Medical image diagnosis has achieved significant progress with deep learning, yet existing methods often rely on isolated visual evidence and lack the ability…
Read free explainer →
#15 · score 89 · 2026-W35
Logarithmic depth compression of Heisenberg Hamiltonian simulation by fan-out parallelization, with built-in error detection
Noisy intermediate-scale quantum computers are constrained by circuit depth, while product-formula simulation of spin systems leads to narrow and deep circuits…
Read free explainer →
#16 · score 89 · 2026-W39
Can 4D Foundation Models Remember?
Perceiving and remembering the visual world is fundamental to navigating and interacting with our environment. Current 4D foundation models, such as camera-con…
Read free explainer →
#17 · score 88 · 2026-W36
Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a r…
Read free explainer →
#18 · score 88 · 2026-W40
SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
Recent research on Multimodal Sentiment Analysis (MSA) has focused on learning from language, visual, and acoustic modalities with incomplete data to infer hum…
Read free explainer →
#19 · score 87 · 2026-W41
Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perce…
Read free explainer →
#20 · score 87 · 2026-W30
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
We introduce DeepSeek-R1, a reasoning model trained with large-scale reinforcement learning that achieves strong multi-step reasoning without extensive human-a…
Read free explainer →
#21 · score 87 · 2026-W34
PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization
Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previ…
Read free explainer →
#22 · score 87 · 2026-W36
Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning
Reliable surgical planning requires models to anticipate not only how instruments will move, but also how the operative visual state will evolve together with…
Read free explainer →
#23 · score 87 · 2026-W38
Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
Many biological discovery problems require experiments to be selected sequentially under constrained budgets. CRISPR screening is a prominent example, as exhau…
Read free explainer →
#24 · score 87 · 2026-W39
Analytic leakage suppression with a single control field: fast two-qubit gates with tunable couplers
Simple analytic pulse-shaping techniques are of great practical utility in quantum control, with prime examples being the DRAG method for suppressing leakage i…
Read free explainer →