New Capability New Capability
333 papers · Page 2 of 4
VectorWorld enables stable, real-time 1km+ closed-loop world model rollouts for autonomous driving using diffusion flow on vector graphs.
AI & ML arxiv | Mar 19
REAL achieves extreme quadruped parkour agility that is robust even to a 1-meter visual blind zone.
AI & ML arxiv | Mar 19
Lifting 2D features into a volumetric representation for robot manipulation policies yields a 14.8% success rate improvement by solving the 2D-3D spatial reasoning mismatch.
AI & ML arxiv | Mar 19
DebugLM allows developers to trace an LLM's specific behaviors back to individual training data sources.
AI & ML arxiv | Mar 19
Enforce formal safety and Signal Temporal Logic (STL) constraints on robotics foundation models without retraining.
AI & ML arxiv | Mar 19
SkeletonLLM allows frozen Multimodal LLMs to reason about human motion by rendering skeleton sequences into their native visual modality.
AI & ML arxiv | Mar 19
Motion-MLLM integrates IMU egomotion data into Video-LLMs to solve the fundamental scale and spatial reasoning ambiguities of purely visual models.
AI & ML arxiv | Mar 19
Engineered modularity via per-layer supervision solves the 'Hydra effect,' allowing for the surgical control of specific model behaviors.
AI & ML arxiv | Mar 20
NANOZK enables verifiable LLM inference with 70x smaller proofs and 24ms verification time using a novel layerwise decomposition.
AI & ML arxiv | Mar 20
Solves the problem of 'co-firing' conflicts in probabilistic ML routing systems using temperature-scaled softmax partitioning.
AI & ML arxiv | Mar 20
MemArchitect introduces a governance layer that decouples memory lifecycle management from LLM weights to prevent 'zombie memories.'
AI & ML arxiv | Mar 20
LLM agents can now autonomously re-identify anonymous individuals by combining sparse, non-identifying cues with public data.
AI & ML arxiv | Mar 20
VISTA decouples hypothesis generation from prompt rewriting to escape the local optima and black-box nature of current automatic prompt optimizers.
AI & ML arxiv | Mar 20
TARo introduces a learnable token-level router that steers frozen LLMs toward structured reasoning at test-time without retraining.
AI & ML arxiv | Mar 20
AcceRL introduces a fully asynchronous, decoupled RL framework for Vision-Language-Action (VLA) models that integrates a plug-and-play world model.
AI & ML arxiv | Mar 20
Generative 3D world models are used to scale Sim-to-Real reinforcement learning for robot Vision-Language-Action (VLA) models.
AI & ML arxiv | Mar 20
Learning to Self-Evolve (LSE) trains LLMs to explicitly improve their own context at test-time via reinforcement learning.
AI & ML arxiv | Mar 20
AFS-Search introduces a training-free closed-loop framework to solve spatial grounding errors in diffusion models like FLUX.1.
AI & ML arxiv | Mar 20
Introduces Action Applicability Policy Optimization to train MLLMs to strategically construct and update visual aids to solve geometry problems.
AI & ML arxiv | Mar 20
Introduces explicit spatial tokens (segmentation/depth) into the autoregressive sequence of LVLMs to enable precise 3D/2D grounding.
AI & ML arxiv | Mar 20
Automates the entire robot training pipeline by using video generation models as motion priors to synthesize both simulation environments and expert trajectories.
AI & ML arxiv | Mar 20
Enables privacy-preserving cross-model inference by using homomorphic encryption and linear alignment to map representations between independently trained LLMs.
AI & ML arxiv | Mar 20
A black-box monitoring system that uses behavioral 'fingerprints' to detect silent updates or identity shifts in LLM API endpoints.
AI & ML arxiv | Mar 20
Provides the first rigorous error certification for Physics-Informed Neural Networks (PINNs), bridging the gap between empirical residual loss and actual solution guarantees.
AI & ML arxiv | Mar 20
Uses Sparse Autoencoders (SAEs) to prove that Vision-Language-Action models learn steerable motion primitives rather than just memorized sequences.
AI & ML arxiv | Mar 20
Introduces the first discrete generation model capable of handling high-dimensional (768-1024 dims) representation tokens.
AI & ML arxiv | Mar 20
Enables continuous Level of Detail (LoD) for 3D Gaussian Splatting without the typical trade-off in full-capacity rendering quality.
AI & ML arxiv | Mar 20
A self-improvement framework (MIPO) that improves LLM personalization and reasoning with zero additional data or human labels.
AI & ML arxiv | Mar 23
VAMPO optimizes visual dynamics in video models using policy gradients to fix precision-critical errors in robotic manipulation.
AI & ML arxiv | Mar 23
Introduces Any-Subgroup Equivariant Networks (ASEN), a single model that can adapt to multiple different symmetry groups via input modulation.
AI & ML arxiv | Mar 23
ICLAD enables unified, in-context anomaly detection for tabular data across unsupervised, semi-supervised, and one-class regimes without weight updates.
AI & ML arxiv | Mar 23
Expands formal reasoning beyond proof construction to the generation and formal verification of counterexamples in Lean 4.
AI & ML arxiv | Mar 23
CurveStream implements a curvature-aware hierarchical memory to handle streaming video in MLLMs without Out-of-Memory (OOM) errors.
AI & ML arxiv | Mar 23
Boosts open-model agent performance on web navigation tasks from 6.4% to 43%, surpassing proprietary models like GPT-4o.
AI & ML arxiv | Mar 23
First unified pipeline to reconstruct complete geometry, materials, and lighting from sparse views in under one second.
AI & ML arxiv | Mar 23
Introduces the first inherently scalable primitive for radiance fields, allowing real-time Level-of-Detail (LOD) rendering by simply truncating Fourier coefficients.
AI & ML arxiv | Mar 23
SCRL introduces the first negative supervision mechanism for Test-Time Reinforcement Learning, preventing LLMs from reinforcing 'consensus lies'.
AI & ML arxiv | Mar 23
X-World is a controllable, action-conditioned multi-camera world model that simulates realistic future video observations for end-to-end driving.
AI & ML arxiv | Mar 23
Enables LLMs to explore beyond their current distribution during RL by treating failed trajectories as hindsight guidance.
AI & ML arxiv | Mar 23
Replaces unstable free-form recursive LLM code with a typed functional runtime grounded in lambda-calculus.
AI & ML arxiv | Mar 23
Enables zero-shot, directed protein generation by applying a simple scalar bias to stochastic attention samplers.
AI & ML arxiv | Mar 23
A comprehensive end-to-end workflow for humanoid loco-manipulation that standardizes sim-to-real transfer.
AI & ML arxiv | Mar 23
An autonomous AI agent that executes end-to-end theoretical and computational physics research, including hypothesis testing and discovery.
AI & ML arxiv | Mar 23
Composes pre-trained unimanual robotic policies into complex bimanual tasks without requiring bimanual demonstration data.
AI & ML arxiv | Mar 24
Sets a new state-of-the-art for intracortical speech decoding with 14.3% phoneme error rate using a multitask Transformer.
AI & ML arxiv | Mar 24
InjectFlow is a training-free method that fixes semantic degradation and bias in Flow Matching models by injecting orthogonal semantics into the velocity field.
AI & ML arxiv | Mar 24
BubbleRAG enables high-precision retrieval-augmented generation over black-box Knowledge Graphs where the schema and structure are unknown.
AI & ML arxiv | Mar 24
WebNavigator reframes autonomous web navigation from probabilistic exploration to deterministic pathfinding, doubling state-of-the-art success rates.
AI & ML arxiv | Mar 24
ALARA for Agents provides a declarative framework for enforcing least-privilege tool access and context scoping in multi-agent systems.
AI & ML arxiv | Mar 24
Claude Opus 4.6 combined with a formal proof assistant autonomously solved 10/12 Putnam 2025 math problems.
AI & ML arxiv | Mar 24
A neural-symbolic pipeline discovers physical conservation laws from data without the false positives that plague previous methods in chaotic systems.
AI & ML arxiv | Mar 24
PAVE introduces an inference-time validation layer that decomposes context into atomic facts to boost RAG accuracy by up to 32 points.
AI & ML arxiv | Mar 24
Swim2Real uses a VLM as a 'closed-loop' feedback mechanism to calibrate complex robotic simulators directly from video.
AI & ML arxiv | Mar 24
MEGA introduces a way to edit LLM knowledge via mechanism-guided activation steering instead of permanent weight modifications.
AI & ML arxiv | Mar 24
BenchBench shifts the focus from model performance to model 'designer' capability by benchmarking automated benchmark generation.
AI & ML arxiv | Mar 24
Contrastive Association Learning (CAL) successfully recovers functional gene associations from expression data where standard similarity metrics fail.
AI & ML arxiv | Mar 24
Dream Diffusion Policy enables robots to survive severe OOD disturbances by detecting reality-imagination discrepancies and switching to an internal world model.
AI & ML arxiv | Mar 24
Cortical Policy introduces a dual-stream view transformer inspired by the human brain's dorsal and ventral pathways to solve complex robotic manipulation.
AI & ML arxiv | Mar 24
LiFR-Seg achieves high-frame-rate semantic segmentation using low-frame-rate cameras by propagating features through asynchronous event streams.
AI & ML arxiv | Mar 24
ORACLE uses symbolic reasoning engines to verify intermediate reasoning steps in synthetic data generation, moving beyond simple answer-correctness filtering.
AI & ML arxiv | Mar 24
AlphaAdj uses a VLM to dynamically adjust Control Barrier Function parameters in real-time for safe and efficient robotic navigation.
AI & ML arxiv | Mar 24
SPECTRE-G2 is a unified anomaly detector that uses eight complementary signals to detect 'unknown unknown' structural anomalies.
AI & ML arxiv | Mar 24
A training-free system for 3D scene reconstruction and editing from sparse RGB images using 3D-aware diffusion models to fill geometric gaps.
AI & ML arxiv | Mar 24
Introduces Reward Sharpness-Aware Fine-Tuning (RSA-FT) to mitigate reward hacking in diffusion models without retraining reward models.
AI & ML arxiv | Mar 24
GIDE enables precise, training-free image editing for discrete Diffusion LLMs by introducing a novel Discrete Noise Inversion mechanism.
AI & ML arxiv | Mar 24
Enables multimodal models to self-evolve their reasoning without human labels or external reward models.
AI & ML arxiv | Mar 24
DRTriton uses large-scale synthetic data and curriculum RL to automatically generate highly optimized Triton kernels, significantly outperforming top-tier LLMs.
AI & ML arxiv | Mar 24
Introduces git-inspired primitives to enable truly asynchronous and non-interfering multi-agent software engineering collaboration.
AI & ML arxiv | Mar 24
Solves the 'recursive drift' problem in self-improving LLMs by using symbolic verification to gate training data quality.
AI & ML arxiv | Mar 24
Transitions MLLMs from reactive planning to 'mental navigation' by forcing the construction of hierarchical cognitive maps from egocentric video.
AI & ML arxiv | Mar 24
HumanOmni-Speaker achieves end-to-end speaker diarization and lip-reading by compressing high-frequency motion residuals into just 6 tokens per frame.
AI & ML arxiv | Mar 24
Achieves zero-shot, zero-training collaborative navigation between humanoid and quadruped robots.
AI & ML arxiv | Mar 24
Introduces a training-free method to visualize and validate the invariances of any feature extractor using diffusion priors.
AI & ML arxiv | Mar 24
Reveals that frozen LLMs contain person-specific 'neural signatures' that can predict individual brain activity.
AI & ML arxiv | Mar 24
Uses the chronological visitation order of medical scans as a self-supervised signal for disease progression modeling.
AI & ML arxiv | Mar 24
Ensures safe Vision-Language Model generation without over-refusal by steering activations within the null-space of benign inputs.
AI & ML arxiv | Mar 24
Integrates LLMs as closed-loop tuning experts for manufacturing robots to achieve 0% failure in complex 3D printing tasks.
AI & ML arxiv | Mar 24
Integrates auction bids and monetization logic directly into generative recommender systems (like TIGER) via bid-aware decoding.
AI & ML arxiv | Mar 24
MemDLM embeds a simulated denoising process into training to create 'Parametric Memory,' narrowing the train-inference gap for Diffusion Language Models.
AI & ML arxiv | Mar 24
A transformer-based meta-amortized framework that allows simulation-based inference to remain valid across different model structures without retraining.
AI & ML arxiv | Mar 24
A grid-free probabilistic framework for nonrigid registration of high-dimensional vector-valued functions on irregular manifolds.
AI & ML arxiv | Mar 24
Small adapters can provide frozen decoder-only LLMs with persistent latent-space memory that survives across separate sessions.
AI & ML arxiv | Mar 25
Introduces a framework for LLMs to self-improve reasoning in specific domains by autonomously mining and constructing training environments directly from the open web.
AI & ML arxiv | Mar 25
Leverages unstructured clinical notes during training to boost the performance of models that are deployed using only structured EHR data.
AI & ML arxiv | Mar 25
CanViT is the first task-agnostic active-vision foundation model that reconstructs scenes using low-resolution 'glimpses' with 19.5x fewer FLOPs than existing models.
AI & ML arxiv | Mar 25
CAM3R is a camera-agnostic 3D reconstruction model that handles fisheye, panoramic, and pinhole imagery without requiring prior calibration.
AI & ML arxiv | Mar 25
A new statistical test that reliably detects whether a dataset was NOT used in an LLM's training corpus.
AI & ML arxiv | Mar 25
ABSTRAL automates the design of multi-agent systems by treating architectures as evolving, inspectable natural-language documents.
AI & ML arxiv | Mar 25
UniQueR reconstructs full 3D scenes (including occluded areas) from unposed images in a single forward pass.
AI & ML arxiv | Mar 25
Deep semi-parametric models allow for the instant deletion of training data from a model without retraining or parameter updates.
AI & ML arxiv | Mar 25
WorldMesh generates consistent, large-scale 3D worlds by populating a geometric mesh scaffold with image diffusion-derived content.
AI & ML arxiv | Mar 25
Identifies that MLLMs fail to perceive visual illusions due to a high-frequency attention bias and provides a plug-and-play fix that boosts accuracy from 13% to 84%.
AI & ML arxiv | Mar 25
Polaris introduces a 'Gödel Agent' framework that allows 7B-parameter models to recursively improve their own policies through auditable code patches.
AI & ML arxiv | Mar 25
Develops a collaborative memory framework that distills agent-agnostic reasoning trajectories, allowing different LLM models to share a single memory system.
AI & ML arxiv | Mar 25
Identifies functionally complete safety circuits in LLMs via differentiable binary masks, allowing for near-surgical removal of backdoors and jailbreaks.
AI & ML arxiv | Mar 25
Uses Sparse Autoencoders (SAEs) to identify and steer cultural representations in LLMs, eliciting rare cultural concepts that prompting alone misses.
AI & ML arxiv | Mar 25
A unified framework that decomposes monolithic 3D meshes into 'sim-ready' interactive articulated assets using a sparse 3D VQ-VAE.
AI & ML arxiv | Mar 25
A generative framework for graphs that closes the fidelity gap between energy-based models and discrete diffusion.
AI & ML arxiv | Mar 25
A bilevel framework where an outer LLM loop meta-optimizes an inner autoresearch loop by autonomously generating and injecting Python code at runtime.
AI & ML arxiv | Mar 25
Integrates tactile perception into video-action models to enable high-fidelity force modulation in contact-rich robotic tasks.
AI & ML arxiv | Mar 25