Related papers: Self-Improving VLM Judges Without Human Annotation…

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contributes to inference latency and operational cost. Recent studies suggest that many real-world…

Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action…

While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking ground-truth verifiers, such as LLM alignment. In this work, we…

The "LLM-as-an-annotator" and "LLM-as-a-judge" paradigms employ Large Language Models (LLMs) as annotators, judges, and evaluators in tasks traditionally performed by humans. LLM annotations are widely used, not only in NLP research but…

LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback),…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their multilingual evaluation…

Training of autonomous driving systems requires extensive datasets with precise annotations to attain robust performance. Human annotations suffer from imperfections, and multiple iterations are often needed to produce high-quality…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Large language models can generate solutions to complex problems, but training them with reinforcement learning typically requires verifiable rewards that are expensive to create and not possible for all domains. We demonstrate that LLMs…

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining…

Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach for improving frozen LLMs via interpretable interventions.…

Vision-Language Models (VLMs) struggle with complex image annotation tasks, such as emotion classification and context-driven object detection, which demand sophisticated reasoning. Standard Supervised Fine-Tuning (SFT) focuses solely on…

While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or partially correct solutions.…

Using a language model to score or rank candidate responses has become a scalable alternative to human evaluation in reinforcement learning from human feedback (RLHF) pipelines, benchmarking, and application layer evaluations. However,…

Reward modeling is crucial for aligning large language models (LLMs) with human preferences, especially in reinforcement learning from human feedback (RLHF). However, current reward models mainly produce scalar scores and struggle to…

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…