research note
HTTP REST API Structure Learning
This paper addresses the challenge of securing HTTP REST APIs by learning their structural behavior directly from observed network traffic, without.
Research
Page 55 of 166
Skip to content
research note
Know Your Source: A Public Knowledge Store for Media Background Checks
This paper addresses the problem of unreliable or biased evidence sources impacting the outputs of large language model (LLM)-based retrieval-augmented.
research note
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
This paper addresses the critical problem of unlearning sensitive memorized data, specifically personally identifiable information (PII), from large.
research note
Neuron-Aware Active Few-Shot Learning for LLMs
This paper addresses the problem of selecting the most informative few-shot examples for adapting large language models (LLMs) to specialized domains with.
research note
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
This paper addresses the challenge of post-training large language models (LLMs) in specialized domains without access to external supervision or.
research note
Online Safety Monitoring for LLMs
The paper addresses the problem that despite alignment training, large language models (LLMs) remain prone to generating unsafe outputs during deployment.
research note
Optimal stellar rank approximation of squeezed cat states with photon catalysis
This paper addresses the challenge of efficiently generating non-Gaussian quantum states, particularly squeezed coherent state superpositions (squeezed.
research note
Physical surfaces make touch interactions in virtual reality precise, efficient, and bimanual
This paper addresses the challenge of achieving precise and efficient touch interactions in virtual reality (VR), where mid-air hand gestures lack tactile.
research note
Real-Time Visual Intelligence on Low-Cost UAVs: A Modular Approach for Tracking, Scanning, and Navigation
This paper addresses the challenge of deploying advanced real-time visual intelligence on low-cost, resource-constrained drones.
research note
Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study
This study investigates what drives first-try reliability in agentic code generation by evaluating 90 independent runs of agents building the same.
research note
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
This paper addresses the challenging task of speaker recognition in long-form TV dramas, where accurately attributing each spoken utterance to the correct.
research note
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
This paper addresses a key challenge in long-context large language model (LLM) use: although models can ingest very long contexts (up to 128K tokens).