PaperHub

Martin Vechev

~Martin_Vechev1

41
论文总数
20.5
年均投稿
5.7
平均评分
接收情况28/41
会议分布
ICLR
24
ICML
9
NeurIPS
8

发表论文 (41 篇)

202525 篇

6.1
4

A Unified Approach to Routing and Cascading for LLMs

ICML 2025Poster
4.0
4

Multi-Neuron Unleashes Expressivity of ReLU Networks Under Convex Relaxation

ICLR 2025withdrawn
6.5
4

Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation

ICLR 2025Poster
4.8
4

AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs

ICLR 2025Rejected
4.8
4

CTBench: A Library and Benchmark for Certified Training

ICLR 2025Rejected
5.2
5

A Unified Approach to Routing and Cascading for LLMs

ICLR 2025Rejected
4.9
4

Automated Benchmark Generation for Repository-Level Coding Tasks

ICML 2025Poster
4.8
3

CTBench: A Library and Benchmark for Certified Training

ICML 2025Poster
4.7
3

Average Certified Radius is a Poor Metric for Randomized Smoothing

ICLR 2025Rejected
7.8
4

Watermarking Autoregressive Image Generation

NeurIPS 2025Poster
7.0
4

Black-Box Detection of Language Model Watermarks

ICLR 2025Poster
6.0
3

Language Models are Advanced Anonymizers

ICLR 2025Poster
6.3
3

Discovering Spoofing Attempts on Language Model Watermarks

ICML 2025Poster
5.5
4

Average Certified Radius is a Poor Metric for Randomized Smoothing

ICML 2025Poster
6.5
4

Ward: Provable RAG Dataset Inference via LLM Watermarks

ICLR 2025Poster
5.6
5

Discovering Clues of Spoofed LM Watermarks

ICLR 2025Rejected
5.5
4

Black-Box Adversarial Attacks on LLM-Based Code Completion

ICLR 2025Rejected
6.1
4

Black-Box Adversarial Attacks on LLM-Based Code Completion

ICML 2025Poster
5.6
5

GRAIN: Exact Graph Reconstruction from Gradients

ICLR 2025Poster
6.1
4

Mind the Gap: A Practical Attack on GGUF Quantization

ICML 2025Poster
7.8
4

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

NeurIPS 2025Poster
4.3
4

Evading Data Contamination Detection for Language Models is (too) Easy

ICLR 2025Rejected
7.0
3

MathConstruct: Challenging LLM Reasoning with Constructive Proofs

ICML 2025Poster
3.3
3

Gaussian Loss Smoothing Enables Certified Training with Tight Convex Relaxations

ICLR 2025Rejected
4.9
4

BaxBench: Can LLMs Generate Correct and Secure Backends?

ICML 2025Spotlight

202416 篇

5.3
3

Programmable Synthetic Data Generation

ICLR 2024Rejected
6.0
5

ConStat: Performance-Based Contamination Detection in Large Language Models

NeurIPS 2024Poster
3.5
4

Human-in-the-loop Detection of AI-generated Text via Grammatical Patterns

ICLR 2024Rejected
7.2
5

Beyond Memorization: Violating Privacy via Inference with Large Language Models

ICLR 2024Spotlight
5.5
4

Understanding Certified Training with Interval Bound Propagation

ICLR 2024Poster
6.3
3

Expressivity of ReLU-Networks under Convex Relaxations

ICLR 2024Poster
5.5
4

Private Attribute Inference from Images with Vision-Language Models

NeurIPS 2024Poster
5.5
4

Prompt Sketching for Large Language Models

ICLR 2024Rejected
6.3
4

SPEAR: Exact Gradient Inversion of Batches in Federated Learning

NeurIPS 2024Poster
7.0
5

Controlled Text Generation via Language Model Arithmetic

ICLR 2024Spotlight
6.0
3

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation

ICLR 2024Poster
5.5
4

Understanding Large Language Models Through the Lens of Dataset Generation

ICLR 2024Rejected
6.2
5

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

ICLR 2024Poster
5.4
5

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents

NeurIPS 2024Poster
6.7
3

DAGER: Exact Gradient Inversion for Large Language Models

NeurIPS 2024Poster
6.5
4

Exploiting LLM Quantization

NeurIPS 2024Poster
合作者 (20)