Papers TAR
“TAR” 태그가 달린 논문 111편 · 필터 해제
Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts i…
TARInfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time--quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior c…
GPUStreaming video understandingTARVideo UnderstandingFinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design
Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficienc…
Answer GenerationArithmetic ReasoningMultimodal ReasoningQuestion-Answer-Generation+1Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily rev…
Meta-LearningTARPrompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-…
Machine UnlearningTARRegret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We pr…
TARvalidBeyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
Multi-agent collaboration has emerged as a pivotal paradigm for addressing complex, distributed tasks in large language model (LLM)-driven applications. While prior research has focused on high-level architectural framew…
Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language Model+12D-3D Attention and Entropy for Pose Robust 2D Facial Recognition
Despite recent advances in facial recognition, there remains a fundamental issue concerning degradations in performance due to substantial perspective (pose) differences between enrollment and query (probe) imagery. Ther…
TARPerson Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait
We address the problem of whole-body person recognition in unconstrained environments. This problem arises in surveillance scenarios such as those in the IARPA Biometric Recognition and Identification at Altitude and Ran…
Face RecognitionPerson RecognitionRTETAR+1A review of DNA restriction-free overlapping sequence cloning techniques for synthetic biology
DNA cloning methods are fundamental tools in molecular biology, synthetic biology, and genetic engineering that enable precise DNA manipulation for various scientific and biotechnological applications. This review system…
TARGIF: Generative Inspiration for Face Recognition at Scale
Aiming to reduce the computational cost of Softmax in massive label space of Face Recognition (FR) benchmarks, recent studies estimate the output using a subset of identities. Although promising, the association between …
Face RecognitionTARA Generalised and Adaptable Reinforcement Learning Stopping Method
This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall an…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)TARReciprocating thermochemical mediator of pre-biotic polymer decomposition on mineral surfaces
A continuing frustration for origin of life scientists is that abiotic and, by extension, pre-biotic attempts to develop self-sustaining, evolving molecular systems tend to produce more dead-end substances than macromole…
TARBridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets
Medical Visual Question Answering (MVQA) systems can interpret medical images in response to natural language queries. However, linguistic variability in question phrasing often undermines the consistency of these system…
DiversityMedical Visual Question AnsweringNatural Language QueriesQuestion Answering+3TAR: Teacher-Aligned Representations via Contrastive Learning for Quadrupedal Locomotion
Quadrupedal locomotion via Reinforcement Learning (RL) is commonly addressed using the teacher-student paradigm, where a privileged teacher guides a proprioceptive student policy. However, key challenges such as represen…
Contrastive LearningReinforcement Learning (RL)TARGenerating Multimodal Driving Scenes via Next-Scene Prediction
Generative models in Autonomous Driving (AD) enable diverse scene creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes fo…
Autonomous Drivingmultimodal generationPredictionTAR$TAR^2$: Temporal-Agent Reward Redistribution for Optimal Policy Preservation in Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning (MARL), learning effective policies is challenging when global rewards are sparse and delayed. This difficulty arises from the need to assign credit across both agents an…
Multi-agent Reinforcement LearningTARLearning with Noisy Triplet Correspondence for Composed Image Retrieval
Composed Image Retrieval (CIR) enables editable image search by integrating a query pair--a reference image ref and a textual modification mod--to retrieve a target image tar that reflects the intended change. While …
Image RetrievalRetrievalTARTripletAgent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning
In multi-agent environments, agents often struggle to learn optimal policies due to sparse or delayed global rewards, particularly in long-horizon tasks where it is challenging to evaluate actions at intermediate time st…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningTARSmartphone-based Iris Recognition through High-Quality Visible Spectrum Iris Capture
Iris recognition is widely acknowledged for its exceptional accuracy in biometric authentication, traditionally relying on near-infrared (NIR) imaging. Recently, visible spectrum (VIS) imaging via accessible smartphone c…
Iris RecognitionTAR