New Capability New Capability
333 papers · Page 4 of 4
Interfaces LLMs with Wikidata-scale graphs for multi-hop reasoning without any retraining of the model or the query executor.
AI & ML arxiv | Apr 1
Achieves an 80x improvement in stable generation length for occupancy world models, enabling 4km+ autonomous driving simulations from a single frame.
AI & ML arxiv | Apr 1
Leverages model reprogramming as an 'active signal amplifier' to proactively audit privacy leakage in LLMs and Diffusion models.
AI & ML arxiv | Apr 1
Achieves a +48pp accuracy gain in agents using a non-parametric online learning framework that reuses procedural plans without updating model weights.
AI & ML arxiv | Apr 1
Introduces a way for diffusion models to generate a single, sharp 'mental average' of a concept rather than blurry pixel-wise averages.
AI & ML arxiv | Apr 1
Introduces a scalable reinforcement learning framework that enables high-fidelity control of a whole-body human musculoskeletal system with over 700 muscles.
AI & ML arxiv | Apr 1
Proposes 'Nomad', an exploration-first agent architecture that autonomously discovers insights in data without being limited by human prompts or questions.
AI & ML arxiv | Apr 1
Provides a robust solution for anti-aliasing in Feed-forward Gaussian Splatting, enabling high-fidelity rendering across varying sampling rates and resolutions.
AI & ML arxiv | Apr 1
Enables precise Camera-LiDAR extrinsic calibration even under massive initial misalignments that typically break automated calibration systems.
AI & ML arxiv | Apr 1
The first prior-fitted foundation model for survival analysis that enables zero-shot time-to-event predictions on tabular data.
AI & ML arxiv | Apr 1
Provides a closed-form safety law for Dynamic Movement Primitives, enabling provably safe robot control without real-time optimization.
AI & ML arxiv | Apr 1
A novel approach to upcycle multiple dense expert models into a unified Mixture-of-Experts model without any additional training.
AI & ML arxiv | Apr 1
Introduces a GUI-native agent system that operates complex scientific instruments through their existing visual interfaces rather than requiring proprietary APIs.
AI & ML arxiv | Apr 1
Enables reinforcement learning for long-horizon robots across diverse tasks without requiring manual reward engineering.
AI & ML arxiv | Apr 2
First generative model capable of synthesizing physically consistent 'raw' camera sensor data from text prompts or sRGB images.
AI & ML arxiv | Apr 2
A production-ready adaptive router for LLM portfolios that manages cost-quality trade-offs in real-time under strict dollar budgets.
AI & ML arxiv | Apr 2
High-quality oversight of massive proprietary LLM agents can be achieved by small, open-source 'critics' that intervene in real-time within the same interaction.
AI & ML arxiv | Apr 2
Reduces multimodal jailbreak success rates by 97% using a simple conditional decoding strategy without task-specific fine-tuning.
AI & ML arxiv | Apr 2
Reconstructs authentic LiDAR point clouds under jamming attacks with a 92% success rate by exploiting raw full-waveform representations.
AI & ML arxiv | Apr 2
Enables zero-shot humanoid navigation in unseen environments using only 5 hours of human walking data and no robot-specific data.
AI & ML arxiv | Apr 2
A white-box membership inference attack using 'gradient-induced feature drift' to outperform all existing confidence-based methods.
AI & ML arxiv | Apr 2
Introduces the first auto-regressive framework for Gaussian Splatting, enabling parallel, progressive next-scale 3D generation.
AI & ML arxiv | Apr 2
Proposes a parameter-efficient LLM adaptation method that enables rapid specialization on non-stationary streams while preventing catastrophic forgetting.
AI & ML arxiv | Apr 2
Rebuilds the Agent-Computer Interaction (ACI) stack for scientific discovery, solving the fragility of JSON tool-calling and execution sandboxes.
AI & ML arxiv | Apr 2
Introduces SIGN, a framework capable of discovering governing symbolic equations for networked systems with over 100,000 nodes.
AI & ML arxiv | Apr 2
TTA-Vid enables video reasoning models to adapt to new domains at test-time using label-free reinforcement learning on a single sample.
AI & ML arxiv | Apr 2
ThoughtSteer demonstrates the first successful backdoor attack on continuous latent reasoning models that leave no token-based audit trail.
AI & ML arxiv | Apr 2
An autonomous research pipeline discovered a lifelong multimodal memory framework by diagnosing and fixing its own architectural bugs and data pipeline issues.
AI & ML arxiv | Apr 2
WARP provides provable, guaranteed repairs for inner layers of Transformers, overcoming the limitation of previous methods restricted to the final layer.
AI & ML arxiv | Apr 2
Solves highly intractable (#P-hard) multi-objective optimization problems with tight approximation guarantees using a novel SAT-oracle approach.
AI & ML arxiv | Apr 2
Demonstrates that covert collusion between multi-agent LLM systems can be detected zero-shot using internal model activations.
AI & ML arxiv | Apr 2
First humanoid robot system to achieve consecutive ping-pong strikes using only onboard egocentric vision and whole-body coordination.
AI & ML arxiv | Apr 2
Introduces 'deconfounding scores' to enable reliable causal effect estimation even when treatment and control groups have very little overlap.
AI & ML arxiv | Apr 2