A framework called Policy-as-Data generates task-oriented synthetic HOI data via RL policies in physics simulators, retargets it, and trains diffusion models that generalize to unseen objects and long horizons.
hub
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Anomalies in eight popular MTSAD benchmarks are predominantly univariate, with no cross-channel ruptures occurring without accompanying univariate deviations, rendering the benchmarks unsuitable for testing cross-channel modeling.
AgroVG is a new multi-source benchmark for agricultural visual grounding formulated as generalized set prediction, with protocols for box and mask grounding across single-target, multi-target, and target-absent queries from six object families.
PopPy combines an ahead-of-time compiler and runtime to extract parallelism from Python compound AI applications, delivering up to 6.4x end-to-end speedups while preserving sequential semantics.
Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
ActPlane introduces an OS-kernel policy engine using an information-flow control DSL and eBPF to enforce agent harness policies, achieving better compliance on indirect paths with 1.9-8.4% overhead.
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
A fixed-width, shared-activation deep network architecture is constructed so that every intermediate readout approximates the target function at a geometrically decaying rate proportional to depth.
Researchers created a stigma-aware WhatsApp chatbot for menstrual health education in Pakistan through co-design workshops and a two-week deployment, yielding insights on its use for challenging taboos alongside tensions around trust and cultural explanations.
Physician oversight reveals high error rates in LLM-generated labels for a clinical benchmark and demonstrates that corrected labels improve both evaluation accuracy and downstream model training.
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
A generative compression model using historical priors for Earth observation data achieves up to 10,000x reduction after exascale training on an Armv9 supercomputer.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics
A framework called Policy-as-Data generates task-oriented synthetic HOI data via RL policies in physics simulators, retargets it, and trains diffusion models that generalize to unseen objects and long horizons.
-
Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate
Anomalies in eight popular MTSAD benchmarks are predominantly univariate, with no cross-channel ruptures occurring without accompanying univariate deviations, rendering the benchmarks unsuitable for testing cross-channel modeling.
-
AgroVG: A Large-Scale Multi-Source Benchmark for Agricultural Visual Grounding
AgroVG is a new multi-source benchmark for agricultural visual grounding formulated as generalized set prediction, with protocols for box and mask grounding across single-target, multi-target, and target-absent queries from six object families.
-
PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications
PopPy combines an ahead-of-time compiler and runtime to extract parallelism from Python compound AI applications, delivering up to 6.4x end-to-end speedups while preserving sequential semantics.
-
Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
-
ActPlane: Programmable OS-Level Policy Enforcement for Agent Harnesses
ActPlane introduces an OS-kernel policy engine using an information-flow control DSL and eBPF to enforce agent harness policies, achieving better compliance on indirect paths with 1.9-8.4% overhead.
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
Layer-wise Geometric Approximation Rates for Deep Networks
A fixed-width, shared-activation deep network architecture is constructed so that every intermediate readout approximates the target function at a geometrically decaying rate proportional to depth.
-
Designing Around Stigma: Human-Centered LLMs for Menstrual Health
Researchers created a stigma-aware WhatsApp chatbot for menstrual health education in Pakistan through co-design workshops and a two-week deployment, yielding insights on its use for challenging taboos alongside tensions around trust and cultural explanations.
-
Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight
Physician oversight reveals high error rates in LLM-generated labels for a clinical benchmark and demonstrates that corrected labels improve both evaluation accuracy and downstream model training.
-
Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
-
Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction
A generative compression model using historical priors for Earth observation data achieves up to 10,000x reduction after exascale training on an Armv9 supercomputer.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
- LoCA: Spatially-Aware Low-Rank Convolutional Adaptation of Vision Foundation Models