Related papers: Minimizing Mismatch Risk: A Prototype-Based Routin…

We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired…

Large language models (LLMs) have opened up enormous opportunities while simultaneously posing ethical dilemmas. One of the major concerns is their ability to create text that closely mimics human writing, which can lead to potential…

Zero-shot reinforcement learning (RL) promises to provide agents that can perform any task in an environment after an offline, reward-free pre-training phase. Methods leveraging successor measures and successor features have shown strong…

More and more end-to-end text spotting methods based on Transformer architecture have demonstrated superior performance. These methods utilize a bipartite graph matching algorithm to perform one-to-one optimal matching between predicted…

Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions, such as undermining students' academic dignity. LLM text detection thus needs to ensure the interpretability of the decision,…

Model merging techniques aim to integrate the abilities of multiple models into a single model. Most model merging techniques have hyperparameters, and their setting affects the performance of the merged model. Because several existing…

With the advent of fluent generative language models that can produce convincing utterances very similar to those written by humans, distinguishing whether a piece of text is machine-generated or human-written becomes more challenging and…

The rapid proliferation of large language models (LLMs) has created an urgent need for robust and generalizable detectors of machine-generated text. Existing benchmarks typically evaluate a single detector on a single dataset under ideal…

LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capability boundary of cutting-edge LLMs and do not require full agent execution, making…

We introduce the concept of decision-focused surrogate modeling for solving computationally challenging nonlinear optimization problems in real-time settings. The proposed data-driven framework seeks to learn a simpler, e.g. convex,…

Retrained large language models (LLMs) have become extensively used across various sub-disciplines of natural language processing (NLP). In NLP, text classification problems have garnered considerable focus, but still faced with some…

Large language models (LLMs) achieve remarkable performance across domains but remain prone to hallucinations and inconsistencies. Retrieval-augmented generation (RAG) mitigates these issues by augmenting model inputs with relevant…

Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable…

Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective MLLM routing therefore requires more than estimating query…

In recent years, text classification methods based on neural networks and pre-trained models have gained increasing attention and demonstrated excellent performance. However, these methods still have some limitations in practical…

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is…

Large language models (LLMs) can produce text that closely resembles human writing. This capability raises concerns about misuse, including disinformation and content manipulation. Detecting AI-generated text is essential to maintain…

Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-time. While conventional RL optimizes policies for fixed…

Automated crash reporting systems generate large volumes of duplicate reports, overwhelming issue-tracking systems and increasing developer workload. Traditional stack trace-based deduplication methods, relying on string similarity,…

Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit…