Related papers: NCV: A Node-Wise Consistency Verification Approach…

Reinforcement Learning (RL) has become a powerful tool for enhancing the reasoning abilities of large language models (LLMs) by optimizing their policies with reward signals. Yet, RL's success relies on the reliability of rewards, which are…

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper…

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that…

Augmenting the multi-step reasoning abilities of Large Language Models (LLMs) has been a persistent challenge. Recently, verification has shown promise in improving solution consistency by evaluating generated outputs. However, current…

We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our approach proceeds in two stages. First, we introduce a…

Evaluating answers from state-of-the-art large language models (LLMs) is challenging: lexical metrics miss semantic nuances, whereas "LLM-as-Judge" scoring is computationally expensive. We re-evaluate a lightweight alternative --…

Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and…

As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex…

To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce…

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs). Unlike supervised learning, it updates the model using…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large vocabularies. We present CSV-Decode, a novel approach that uses geometric upper bounds to construct…

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confined to a single, static observation. We propose Thinking with Novel Views (TwNV), a…

Many machine learning algorithms require precise estimates of covariance matrices. The sample covariance matrix performs poorly in high-dimensional settings, which has stimulated the development of alternative methods, the majority based on…

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…