1 citations · 1 across the 8 of their papers we have counts for
12 papers
Prompt-Injection Probes Learn the Conversation, Not Just the Injection
Kaan Kale, Sriram Vishwanath
Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and send suspicious ones to a slower…
WaveCommitments: Private and Verifiable Speech-Agent Marketplaces
Oguzhan Baser, Kaan Kale, Sriram Vishwanath +1
Modern speech systems are evolving into ecosystems of autonomous speech agents that interact, negotiate, and trade assets such as embeddings, spectrograms, or raw data. In such mar…
ModalFidelity: Routing Modalities for Deepfake Detection on a Budget
Oguzhan Baser, Kaan Kale, Sriram Vishwanath +1
Deepfakes no longer need to fake a whole video. Generators that read the transcript now alter only the few seconds in which a video's meaning turns, so a forgery hides in a small,…
The Key Handoff: Retrieval in Hybrid Language Models
Kaan Kale, Oguzhan Baser, Sriram Vishwanath
A two-hop question makes a language model retrieve twice: once to produce a bridge entity, and once to retrieve with it. Transformers resolve that entity in their early layers. Hyb…
RoboShape: Information-Theoretic Point Cloud Representations for Privacy-Aware Robot Perception
Oguzhan Baser, Mirac Sozen, Kaan Kale +2
With the increased adoption of robotic agents operating in human environments by scanning and sharing 3D representations (e.g., for fleet learning, cloud-based planning, or collabo…
VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
Ninghan Zhong, Ahmet Ege Tanriverdi, Kaan Kale +1
Multi-step reasoning with Chain-of-Thought (CoT) prompting remains fragile: logical errors or hallucinations in early steps silently propagate, producing confident but incorrect co…
ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings
Prithwish Jana, Kaan Kale, Ahmet Ege Tanriverdi +3
Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most sta…
Fair Resource Allocation for Fleet Intelligence
Oguzhan Baser, Kaan Kale, Po-han Li +1
Resource allocation is crucial for the performance optimization of cloud-assisted multi-agent intelligence. Traditional methods often overlook agents' diverse computational capabil…
WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing
Oguzhan Baser, Ahmet Ege Tanriverdi, Kaan Kale +2
Speech embeddings often retain sensitive attributes such as speaker identity, accent, or demographic information, posing risks in biased model training and privacy leakage. We prop…
MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
Noel Elias, Homa Esfahanizadeh, Kaan Kale +2
Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train…
SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures
Oguzhan Baser, Kaan Kale, Sandeep P. Chinchali
Advancements in DeepFake (DF) audio models pose a significant threat to voice authentication systems, leading to unauthorized access and the spread of misinformation. We introduce…
TexShape: Information Theoretic Sentence Embedding for Language Models
Kaan Kale, Homa Esfahanizadeh, Noel Elias +3
With the exponential growth in data volume and the emergence of data-intensive applications, particularly in the field of machine learning, concerns related to resource utilization…