Related papers: MVR-cache: Optimizing Semantic Caching via Multi-V…

Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches…

Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions…

Parallel test-time scaling, which generates multiple candidate solutions for a single problem, is a powerful technique for improving large language model performance. However, it is hindered by two key bottlenecks: accurately selecting the…

Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question…

We propose the Multi-modal Untrimmed Video Retrieval task, along with a new benchmark (MUVR) to advance video retrieval for long-video platforms. MUVR aims to retrieve untrimmed videos containing relevant segments using multi-modal queries.…

Composed Image Retrieval (CIR) aims to retrieve target images based on a reference image and modified texts. However, existing methods often struggle to extract the correct semantic cues from the reference image that best reflect the user's…

Leveraging query variants (QVs), i.e., queries with potentially similar information needs to the target query, has been shown to improve the effectiveness of query performance prediction (QPP) approaches. Existing QV-based QPP methods…

Multi-view Stereo (MVS) with known camera parameters is essentially a 1D search problem within a valid depth range. Recent deep learning-based MVS methods typically densely sample depth hypotheses in the depth range, and then construct…

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk…

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

Deep learning recommendation models (DLRMs) are widely used in industry, and their memory capacity requirements reach the terabyte scale. Tiered memory architectures provide a cost-effective solution but introduce challenges in…

Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retrieval applications. In multi-vector retrieval systems, both…

In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The variational semantic memory accrues and stores semantic information for the probabilistic inference of…

Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language models (VLMs) to augment rewards of a task with visual…

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for enhancing the reasoning capabilities of Large Language Models (LLMs). Despite its efficacy, RLVR faces a meta-learning bottleneck: it lacks…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…