Tag

DriveZero: End-to-End Driving Beyond Human Demonstrations

Trains end-to-end driving without human trajectory supervision by decoupling perception and action: DriveVFM distills multiple frozen vision foundation models into a single camera backbone, and DriveRL trains a privileged closed-loop RL teacher whose rollouts supervise a camera-only planner, yielding state-of-the-art closed-loop benchmark results.

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents

Defines the Discovery Certification Protocol (DCP) to audit claims of discovery by AI research agents, converting claims into executable recovery and feedback tests. Specifies multi-gate certification, Core control requirements, and a deterministic offline verifier; validated in two controlled audits.

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Trains LVLMs to improve 3D spatial reasoning using a synthetic block-stacking dataset of 15,000 problems that cover 3D→2D projection, viewpoint transforms, and structural combination; includes color-anchored cues and provides code and data.

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Investigates long-horizon memorization in language models by evaluating how complementary continual-learning mechanisms (data, function, weight anchors and low-rank allocation/LoRA) compose to reduce catastrophic forgetting across 100 sequential tasks; best composition raises final retention from 1.2% to 34.9%.

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

Evaluates whether AI agents can autonomously use Sparse Autoencoders (SAEs) to discover interpretable features and causally steer model behavior. Introduces a 20-task benchmark that has agents design contrastive probes to search a 131K+ feature dictionary in Gemma-2-9B-IT and evaluates activation rank, selectivity, and causal steering against expert references.

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Evaluates a weak teacher's RL-induced policy shift on the student's own rollouts and amplifies verifier-supported updates so stronger models can learn from weaker supervisors and surpass them. It rescales only verifier-supported policy-gradient components to preserve optimization fixed points while accelerating learning, reducing student updates versus standard RL or distillation.

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

Adds a Next Concept Prediction objective that predicts discrete, product-quantized latent concepts spanning multiple tokens alongside next-token prediction, yielding faster pretraining convergence and measurable downstream gains with an 8.9B-parameter latent-space LLM.

Show-Harness: Just a VLM Agent Can Play Robots

Lets vision-language models control robots via a compact semantic action interface that maps intent to discrete action units; supports zero-shot use of closed-source VLMs, low-cost fine-tuning of open VLMs, and GUI-based demonstration collection.

Programmable World Model

Translates natural-language instructions into executable programs that maintain an explicit, persistent global world state and compiles state-augmented 3D oriented bounding boxes into pixel-aligned conditioning signals for pretrained video generators. The approach decouples state evolution from rendering, enabling programmable entity control, off-screen state, and long-horizon interactive scenarios.

arXiv Complete Corpus

Snapshot delivery of arXiv metadata, submission files and rendered documents in multiple Parquet configs (metadata, paper_text, latex, source, pdf, ps). Includes ~3.15M papers, full-text TeX assemblies and indexes to fetch large assets for training, retrieval and analysis.

Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

Suppresses grid-like and granular “digital ripple” artifacts introduced by iterative reference-conditioned image editing using selective spectral notching, structure-aware smoothing, and cleaned-reference regeneration. Prioritizes low-distortion filtering when artifacts are spectrally separable and visual reconstruction when artifacts overlap content.

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Defines recursive self-improvement (RSI) with an evaluation metric (Headroom-Closed Index) and a five-level autonomy roadmap—from executing human-specified improvements to recursively improving improvement mechanisms—while analyzing scenarios, verification challenges, and governance risks.