AI & Machine Learning

GIFT bootstraps image-to-CAD generation by turning inference-time failures into synthetic training data, reducing inference compute by 80%.

A modular, JAX-based framework and taxonomy for Reinforcement Learning with Diffusion and Flow policies.

Achieves high-quality 3D reconstruction and camera pose estimation from sparse views without any pre-trained priors or ground-truth annotations.

Near-lossless KV cache compression using angular quantization in the Walsh-Hadamard domain at ~3.5 bits per element.

Mechanistic analysis reveals that over-refusal and harmful-intent refusal in LLMs occupy distinct representation subspaces.

Introduces 'Hidden Ads,' a new class of semantic backdoor attacks that inject promotional content into VLM responses based on natural user behavior.

Shifts protein fitness optimization from continuous embeddings to discrete Quadratic Unconstrained Binary Optimization (QUBO).

Introduces LongCat-Next, a 'Native Multimodal' model that treats vision and audio as first-class discrete tokens rather than language-centric attachments.

Achieves zero-shot, prompt-free object removal in diffusion models purely through self-attention manipulation.

VoxAnchor uses mmWave radar to authenticate speech by matching acoustics to physical throat vibrations.

RAGent enables training-free, deployment-time human activity recognition for mmWave radar using agentic reasoning.

Proposes SOL-Nav, which replaces raw visual features in navigation with structured language descriptions for LLM-based agents.

Bridges the gap between free-form natural language and safety-critical UAV navigation using Signal Temporal Logic (STL) translation and repair.

Sci-Mind introduces an 'Adversarial Cognitive Dialectic' where specialized agents debate to refine mathematical models.

Achieves a 79,000x reduction in energy per inference for insulin dose calculation using Spiking Neural Networks (SNNs).

Introduces 'Umwelt Engineering,' the deliberate constraint of an agent's linguistic environment to improve reasoning.

PRBench reveals that current top-tier coding agents have a 0% success rate in end-to-end physics paper reproduction.

Introduces Composer, a paradigm that generates input-specific parameter adaptations at inference time to enable dynamic per-input model specialization.

Kuaishou releases KAT-Coder-V2, an agentic coding model achieving state-of-the-art results on SWE-bench Verified through a 'Specialize-then-Unify' paradigm.

Provides empirical evidence and a mechanistic explanation for why LoRA drastically reduces catastrophic forgetting in sequential fine-tuning compared to full fine-tuning.

TianJi is the first 'AI meteorologist' system capable of autonomously driving complex numerical models to verify physical hypotheses in atmospheric science.

A controlled study proving that the temporal organization (curriculum) of multimodal data is a first-order variable in balancing reasoning vs. OCR capabilities.

SkyNet extends MuZero to partially-observable stochastic games by adding auxiliary belief-aware heads, significantly outperforming baselines in complex card games.

Heracles uses a state-conditioned diffusion middleware to bridge precise motion tracking with generative recovery for humanoid robots.

Sortify is the first fully autonomous LLM agent deployed in production for closed-loop recommendation ranking optimization.

AutoStan demonstrates a CLI coding agent that autonomously builds and iteratively improves interpretable Bayesian models in Stan.

Identifies emergent social risks in multi-agent systems, such as spontaneous collusion and conformity, that occur even when agents are not explicitly instructed to do so.

Uses spectral decomposition of inverse dynamics to enable real-time planning of long-horizon robotic manipulation tasks (10+ contact modes).

Introduces SCOUT, a routing framework that intelligently selects which Image-to-3D reconstruction model to use based on input difficulty and cost constraints.

GraySense enables geospatial object tracking using only encrypted network packet sizes without any access to raw video streams.

KVSculpt moves beyond simple eviction/merging to optimize unconstrained KV pairs in continuous space for extreme cache compression.

A rigorous analysis of the AIMO 3 math competition reveals that raw model capability dominates inference-time prompt optimization by an order of magnitude.

Wan-R1 successfully applies Group Relative Policy Optimization (GRPO) to flow-based video models to enable verifiable spatial reasoning.

The eigenvalue tail index of a neural network's weight matrices serves as a near-perfect (R^2 = 0.984) diagnostic for label noise in the training data.

Poppy provides a training-free way to refine monocular surface normals using single-shot polarization measurements at test time.

SAGE mitigates multimodal hallucinations by monitoring 'attention sinks' and dynamically modulating self-attention during the decoding process.

ATLAS-RTC introduces token-level runtime control that detects and corrects LLM drift from structured output contracts during the forward pass.

Guardrails successfully implements and flight-tests Control Barrier Functions on an F-16 fighter jet to enforce safety limits in real-time.

ITQ3_S achieves high-fidelity 3-bit LLM inference by using rotation-domain smoothing to eliminate the catastrophic precision loss caused by outliers.

The Physics-Guided Transformer (PGT) embeds physical priors (like diffusion and causality) directly into the self-attention mechanism via heat-kernel biases.

Iterative Motion Imitation enables bicycle robots to perform unassisted front-flips by learning from initially 'impossible' reference motions.

Proteina-Complexa unifies generative flow-based modeling with structure-based 'hallucination' to set a new SOTA in atomistic protein binder design.

ExFusion enables Transformer models to gain the capacity of Mixture-of-Experts during training while remaining a standard dense model for deployment.

SARL improves reasoning models by rewarding the 'topology' of thoughts rather than just the final answer, enabling effective RL without ground-truth labels.

Dataset Concentration (DsCo) achieves nearly lossless dataset reduction by aligning distributions via diffusion models, cutting storage and training costs by half.

Correlated Diffusion replaces independent noise with structured MCMC dynamics, enabling generative modeling on hyper-efficient probabilistic computers.

This study challenges the common 'best practice' of atomic decomposition for LLM judges, showing that holistic evaluation is often superior at detecting incompleteness.

An autonomous agent reveals that domain-specific molecular architectures are largely unnecessary; standard transformers with better tuning outperform custom designs.

Decoupled language models reduce the compute required for OCR domain adaptation by 95% while matching SOTA transformer accuracy.

This paper clarifies that Diffusion Maps (DMAPs) are not actually a dimensionality reduction tool, but rather a spectral representation that requires specific combinations to form a chart.