AI & Machine Learning

SPINNER is a tri-rotor UAV that uses continuous self-rotation to expand the field of view of its sensors without adding extra hardware.

Medical AI Scientist is the first autonomous framework for clinically grounded research ideation and manuscript drafting.

ResAdapt learns a per-frame visual budget allocator that optimizes input resolution before encoding.

LACE enables continual learning models to automatically expand their own capacity by monitoring loss signals during training.

PRCO decouples perception and reasoning in Multimodal RL through an Observer-Solver architecture.

This paper establishes the formal information-theoretic limits and conditions under which self-improving AI systems can be safely verified.

RNNs can be trained online without Jacobian propagation, matching BPTT performance at 1000x less memory.

Sparse Autoencoders (SAEs) fail at compositional generalization due to flawed dictionary learning, not the inference method.

SOLE-R1 uses Vision-Language Model chain-of-thought reasoning as the sole reward signal for zero-shot robotic reinforcement learning.

IF4 introduces an adaptive 4-bit data type that switches between Float and Integer representations to minimize quantization error.

Vision-Language Models (VLMs) can outperform specialized learning-based placers in chip floorplanning through visual evolutionary optimization.

HyperP provides the first hyperparameter transfer laws for hypersphere optimization, ensuring stable scaling for models using the Muon optimizer.

DreamLite enables sub-second 1024x1024 image generation and editing on mobile devices using a unified 0.39B parameter model.

Metric Similarity Analysis (MSA) uses Riemannian geometry to compare the intrinsic geometry of neural representations.

Challenges a core constraint in statistical learning theory by proving that optimal $\sqrt{N}$ convergence is achievable for offline policy learning even with model classes that exceed the standard Donsker complexity limit.

AI has hit a wall, and it's because data is acting like a heavy anchor slowing the whole thing down.

This new math trick just crushed a massive logistics nightmare that used to take two weeks; now it’s done in 19 minutes.

Computers have gotten so fast at finding the best route on a map that it basically costs them zero effort now, no matter how big the city.

Someone finally built computer memory that doesn't go blank when you pull the plug—it just stays there forever.

Turns out, putting a cheap AI under an AI 'boss' actually makes the work worse unless the boss is way, way smarter than the worker.

AI agents are finding multi-million dollar holes in bank code that even the best human experts completely walked past.

Prunes 85% of visual tokens in Vision-Language-Action (VLA) models while retaining 94% accuracy for autonomous driving.

Introduces a CNN architecture where feature maps are mathematically identical to Grad-CAM saliency maps by design, rather than post-hoc.

Releases weights for LEMON, a foundation model for single-cell nuclear morphology trained on millions of pathology images.

A decentralized system that automates ML research and trains domain-expert 1.58-bit ternary models for CPU-native inference.

Extracts dense 3D Signed Distance Fields from images in under 3 seconds using feed-forward geometry transformer latents.

Uses the Minimum Description Length principle to predict exactly when neural networks will transition from simple 'spurious' shortcuts to complex features.

Modulates LLM hidden states with eye-gaze data to outperform GPT-4o by 10.5 points on streaming video understanding.

Proves that safety probes can detect 'liars' (models hiding harm) but are fundamentally blind to 'fanatics' (models that believe harm is good).

Parallelizes diffusion model sampling across multiple devices using a draft-and-refine process for up to 3.7x speedups.

Shifts world model evaluation from visual fidelity to 'Simulative Reasoning,' revealing a massive gap in current AI's ability to plan.

Learns high-level symbolic state machines directly from raw pixels to guide robot control without hand-crafted priors.

Resolves a long-standing open problem in bandit theory by achieving optimal dynamic regret without knowing the number of environment switches.

Introduces a discrete-ratio selector for context compression that solves the problem of variable information density in long-form text.

Fixes physically impossible video generation by disentangling semantic prompts from physical dynamics during training.

Achieves state-of-the-art video understanding without the need for expensive human-annotated Chain-of-Thought (CoT) data.

Proves that standard 'wisdom' like Chain-of-Thought and Few-Shot prompting actually degrades performance in specialized medical LLMs.

The first large-scale benchmark for LLM agents based on years of authentic, cross-domain user behavioral data rather than synthetic personas.

Demonstrates that symbolic event primitives (like Schank's Conceptual Dependency) can be 'rediscovered' by neural networks purely through compression pressure.

Releases a composable, Optax-native stack that makes high-overhead second-order optimization methods (like K-FAC) practical and swappable.

A billion-scale time-series benchmark that identifies a 'context-length crossover' where foundation models start to crush deep learning baselines.

Introduces a self-driven collaboration paradigm where an agent uses its own 'reflection' signals to escalate difficult tasks to a stronger model tier.

Challenges the assumption that 'background' pixels are useless in GUI agents and identifies a 'recency effect' for optimal token pruning.

Identifies specific hidden-state dimensions (H-Nodes) responsible for hallucinations and introduces a real-time defense to cancel them.

Integrates radiologist gaze data as a probabilistic prior to align vision-language models with actual human clinical reasoning workflows.

Moves industrial recommendation systems from static multi-stage pipelines to self-evolving agentic loops.

Finds that while frontier LLMs can model the mental states of others, they fundamentally fail at self-modeling without explicit reasoning steps.

Introduces ReinPatch, the first framework to jointly optimize sequence tokenization and backbone models using reinforcement learning.

Discovers that object-centric information in Vision Transformers is distributed across all attention components (q, k, v) and layers, not just the final layer.

Releases DataFlex, a unified open-source framework for data-centric dynamic training (selection, mixture, and reweighting) for LLMs.