New research probes LLM context understanding and confidence calibration
作者PulseAugur 编辑部·[113 个来源]·
Researchers are developing new methods to evaluate and enhance Large Language Models (LLMs). Apple's research proposes a benchmark to test LLMs' understanding of context, finding that quantized models and pre-trained dense models struggle with nuanced contextual features. Meanwhile, a new technique called Retrieval-Augmented Linguistic Calibration (RALC) improves how LLMs express confidence in their answers, enhancing faithfulness and calibration. Other research explores LLMs for clinical action extraction, demonstrating comparable performance to supervised models but highlighting limitations in clinical reasoning, and introduces Listwise Policy Optimization for more stable and diverse LLM training.
AI
影响
New benchmarks and calibration techniques aim to improve LLM reliability and reasoning, potentially impacting their application in critical domains like healthcare and scientific discovery.
排序理由
The cluster contains multiple academic papers and research initiatives focused on evaluating and improving LLM capabilities.
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various domains within the realm of Natural Language …
Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual…
Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual…
arXiv:2605.06139v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient is prevalent,…
arXiv:2605.06191v1 Announce Type: new Abstract: The work in this paper evaluates zero-shot and few-shot large language models (LLMs) for safety-critical clinical action extraction using the CLIP discharge-note dataset, with particular emphasis on transitions of care and post-disc…
arXiv cs.AI
TIER_1English(EN)·Aritra Roy, Kevin Shen, Andrew MacBride, Awwal Oladipupo, Mudassra Taskeen, Wojtek Treyde, Ruaa A. E. A. Abakar, Ahmad D. Abbas, Elsayed Abdelfatah, Abbas A. Abdullahi, Seham S. Abyah, Chahd Rahyl Adjmi, Fariha Agbere, Savyasanchi Aggarwal, Muhammad Ahmed·
arXiv:2605.03205v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in a…
arXiv:2602.23547v2 Announce Type: replace Abstract: Sentences like "She will go to France or Spain, or perhaps to Germany or France." appear formally redundant, yet become acceptable in contexts such as "Mary will go to a philosophy program in France or Spain, or a mathematics pr…
arXiv:2605.04886v1 Announce Type: new Abstract: This position paper argues that the under-representation of social science tasks in contemporary LLM benchmarks limits advances in both LLM evaluation and social scientific inquiry. Benchmarks -- standardized tools for assessing com…
This position paper argues that the under-representation of social science tasks in contemporary LLM benchmarks limits advances in both LLM evaluation and social scientific inquiry. Benchmarks -- standardized tools for assessing computational systems -- are pivotal in the develop…
arXiv cs.CL
TIER_1English(EN)·Mengchu Li, Jin Zhu, Jinglai Li, Chengchun Shi·
arXiv:2605.03723v1 Announce Type: new Abstract: The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification …
arXiv:2605.02335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communicate and deliberate through natural language. Yet fluent language use does not b…
arXiv cs.AI
TIER_1English(EN)·Jay Bhan, Nicole Nobili, Srinivasan Raghuraman, Patrick Langer·
arXiv:2605.01120v1 Announce Type: new Abstract: The Zarankiewicz number $\textbf{Z}(m, n, s, t)$ is the maximum number of edges in a bipartite graph $G_{m, n}$ such that there is no complete $K_{s, t}$ bipartite subgraph. We determine for the first time the exact values of three …
The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an entire passage; however, this is insuffic…
arXiv:2605.00327v1 Announce Type: cross Abstract: In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-…
arXiv cs.CL
TIER_1English(EN)·Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska, Jaroslaw A. Chudziak·
arXiv:2605.01416v1 Announce Type: cross Abstract: The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, of…
arXiv cs.CL
TIER_1English(EN)·Luo Ji, Qi Qin, Ningyuan Xi, Teng Chen, Qingqing Gu, Hongyan Li·
arXiv:2605.01973v1 Announce Type: new Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalab…
arXiv cs.CL
TIER_1English(EN)·Xuemei Tang, Xufeng Duan, Zhenguang G. Cai·
arXiv:2605.01846v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position…
Large Language Models (LLMs) have transformed agent-agent and human-agent interaction by enabling software, physical, and simulation agents to communicate and deliberate through natural language. Yet fluent language use does not by itself yield socially intelligible behaviour. Mo…
arXiv cs.CL
TIER_1English(EN)·Zhongyi Zhou, Kohei Uehara, Haoyu Zhang, Jingtao Zhou, Lin Gu, Ruofei Du, Zheng Xu, Tatsuya Harada·
arXiv:2508.04086v2 Announce Type: replace Abstract: Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data gener…
Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signa…
Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases during generation. Through extensive exp…
arXiv:2604.27092v1 Announce Type: new Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based ag…
arXiv:2604.27410v1 Announce Type: cross Abstract: Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle…
arXiv cs.CL
TIER_1English(EN)·Yuxi Ma, Jieming Cui, Muyang Li, Ye Zhao, Yu Li, Yixuan Wang, Chi Zhang, Yinyin Zang, Yixin Zhu·
arXiv:2604.27846v1 Announce Type: new Abstract: How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools mis…
arXiv cs.AI
TIER_1English(EN)·Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre·
arXiv:2601.06394v4 Announce Type: replace-cross Abstract: Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to mo…
arXiv cs.AI
TIER_1English(EN)·Mohd Sameen Chishti, Damilare Peter Oyinloye, Jingyue Li·
arXiv:2604.27789v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates…
arXiv:2604.27996v1 Announce Type: new Abstract: This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three prima…
In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback negatives and sharpen preference boundari…
This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three primary interaction paradigms, including domain-speci…
How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural methods, yet remain fragmented: dictionary tools miss discourse structure, while embeddings conflate…
Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously through provider-side updates without explicit version changes. These silent updates can introduce behavioral drift, causing regressio…
Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to capture nuanced context-specific attribute rel…
arXiv:2604.26577v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful inst…
arXiv cs.AI
TIER_1English(EN)·Nayoung Choi, Haeyu Jeong, Changbong Kim, Hongjun Lim, Jinho D. Choi·
arXiv:2604.26120v1 Announce Type: new Abstract: Behavioral logs provide rich signals for user modeling, but are noisy and interleaved across diverse intents. Recent work uses LLMs to generate interpretable natural-language personas from user logs, yet evaluation often emphasizes …
arXiv:2601.17617v3 Announce Type: replace-cross Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understanding of how agentic search sessions unfold and how retrieved evidence is reflect…
arXiv cs.AI
TIER_1English(EN)·Matteo Leonesi, Francesco Belardinelli, Flavio Corradini, Marco Piangerelli·
arXiv:2604.26511v1 Announce Type: cross Abstract: Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational sett…
arXiv cs.CL
TIER_1English(EN)·Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis, Diogo Fernandes Costa Silva, Arlindo Rodrigues Galv\~ao Filho·
arXiv:2601.04389v2 Announce Type: replace Abstract: Current safety evaluations of large language models (LLMs) create a dangerous illusion of universal protection by aggregating harms under generic categories such as "Identity Hate", obscuring vulnerabilities toward specific popu…
arXiv:2604.26361v1 Announce Type: new Abstract: Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accu…
Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions spanning nine prohibited behavior categ…
Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) …
Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) …
Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audiences. To accomplish this, the textual content in the graphic designs needs to be accurately translated and have the text styling pres…
arXiv:2604.25053v1 Announce Type: new Abstract: While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma toward individuals with psychological conditions. Existing evaluations of this sti…
arXiv:2604.25130v1 Announce Type: new Abstract: Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement,…
arXiv cs.CL
TIER_1English(EN)·Youngjoon Jang, Chanhee Park, Hyeonseok Moon, Young-kyoung Ham, Jiwon Moon, Jinhyeon Kim, JuKyung Jung, Heuiseok Lim·
arXiv:2604.25297v1 Announce Type: new Abstract: In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domain-specialized LLMs are developed using datasets and …
arXiv:2604.24804v1 Announce Type: cross Abstract: Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these meth…
arXiv cs.LG
TIER_1English(EN)·Zhezheng Hao, Hong Wang, Haoyang Liu, Jian Luo, Jiarui Yu, Hande Dong, Qiang Lin, Can Wang, Jiawei Chen·
arXiv:2510.10150v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, its training is often plagued by \emph{entropy collapse},…
In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domain-specialized LLMs are developed using datasets and training protocols that are not aligned with the…
In recent years, the rapid proliferation of open-source large language models (LLMs) has spurred efforts to turn general-purpose models into domain specialists. However, many domain-specialized LLMs are developed using datasets and training protocols that are not aligned with the…
arXiv cs.AI
TIER_1English(EN)·Luca Cotti, Anisa Rula, Devis Bianchini, Federico Cerutti·
arXiv:2509.00081v2 Announce Type: replace-cross Abstract: Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and inte…
arXiv:2602.12134v2 Announce Type: replace Abstract: Existing work on value alignment typically characterizes value relations statically, ignoring how alignment interventions, such as prompting, fine-tuning, or preference optimization, reshape the broader value system. In practice…
arXiv:2604.23296v1 Announce Type: new Abstract: Aspect Sentiment Quad Prediction (ASQP) has seen significant advancements, largely driven by the powerful semantic understanding and generative capabilities of large language models (LLMs). However, while syntactic structure informa…
arXiv:2511.07410v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have become popular tools for embodied high-level planning. However, their deployment in black-box settings often leads to unpredictable or costly errors. To h…
arXiv:2604.24178v1 Announce Type: new Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight c…
arXiv cs.CL
TIER_1(AF)·Abbas Zeitoun, Lucas Torroba-Hennigen, Yoon Kim·
arXiv:2604.21254v2 Announce Type: replace-cross Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model…
arXiv:2604.13006v2 Announce Type: replace Abstract: Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or comm…
arXiv:2604.08568v2 Announce Type: replace Abstract: The evolution of writing assistance tools from machine translation to large language models (LLMs) has changed how researchers write. This study investigates whether this shift is homogenizing research papers by analyzing native…
arXiv cs.CL
TIER_1English(EN)·Miriam Winkler, Verena Blaschke, Barbara Plank·
arXiv:2603.15130v2 Announce Type: replace Abstract: Indirectness is a common feature of daily communication, yet is underexplored in NLP research for both low-resource as well as high-resource languages. Indirect Question Answering (IQA) aims at classifying the polarity of indire…
arXiv:2509.20086v2 Announce Type: replace Abstract: Phonemization is a critical component in text-to-speech synthesis. Traditional approaches rely on deterministic transformations and lexica, while neural methods offer potential for higher generalization on out-of-vocabulary (OOV…
arXiv cs.CL
TIER_1English(EN)·Jisoo Yang (Chung-Ang University), Jongwon Ryu (Chung-Ang University), Minuk Ma (University of British Columbia), Trung X. Pham (Van Lang University), Junyeong Kim (Chung-Ang University)·
arXiv:2604.24079v1 Announce Type: new Abstract: Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylistic cues, treating dialogue as a flat sequence of tok…
arXiv cs.CL
TIER_1English(EN)·Nikita Borovkov, Elisei Rykov, Olga Tsymboi, Sergei Filimonov, Nikita Surnachev, Dmitry Bitman, Anatolii Potapov·
arXiv:2604.23855v1 Announce Type: new Abstract: We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The approach is scalable in production and reaches selective automation within two we…
arXiv:2604.23543v1 Announce Type: new Abstract: Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a promine…
arXiv:2604.23356v1 Announce Type: new Abstract: Large language models (LLMs) show promise in medical diagnosis, but real-world deployment remains challenging due to high-stakes clinical decisions and imperfect reasoning reliability. As a result, careful inspection of model behavi…
arXiv:2604.23255v1 Announce Type: cross Abstract: Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. An…
arXiv:2604.22888v1 Announce Type: cross Abstract: Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already fun…
arXiv cs.AI
TIER_1English(EN)·Ashmi Banerjee, Adithi Satish, Wolfgang W\"orndl, Yashar Deldjoo·
arXiv:2604.24158v1 Announce Type: new Abstract: Evaluating nuanced conversational travel recommendations is challenging when human annotations are costly and standard metrics ignore stakeholder-centric goals. We study LLMs-as-Judges for sustainable city-trip lists across four dim…
arXiv cs.AI
TIER_1English(EN)·Abid Talukder, Maruf Ahmed Mridul, Oshani Seneviratne·
arXiv:2604.23090v1 Announce Type: new Abstract: Automatically generating formal ontologies from unstructured natural language remains a central challenge in knowledge engineering. While large language models (LLMs) show promise, it remains unclear which architectural design choic…
arXiv cs.LG
TIER_1English(EN)·Lawrence Phillips, Marc Boubnovski Martell, Aditya Misra, Josefa Lia Stoisser, Cesar A. Prada-Medina, Rory Donovan-Maiye, Kaspar M\"artens·
arXiv:2509.25346v2 Announce Type: replace-cross Abstract: Predicting cellular responses to genetic perturbations represents a fundamental challenge in systems biology, critical for advancing therapeutic discovery and virtual cell modeling. While large language models (LLMs) show …
arXiv cs.LG
TIER_1English(EN)·Wei Chen, Yubing Wu, Junmei Yang, Delu Zeng, Qibin Zhao, John Paisley, Min Chen, Zhou Wang·
arXiv:2604.18239v2 Announce Type: replace Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based objectives suppress the chosen response along with the rejected one, a phenomenon known as likelihoo…
Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement, preventing effective refinement in applications…
Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and produce aggregate scores without explaining deficiencies or guiding improvement, preventing effective refinement in applications…
While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma toward individuals with psychological conditions. Existing evaluations of this stigma primarily rely on multiple-choice questions …
Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight construction strategies. However, rigidly alignin…
Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylistic cues, treating dialogue as a flat sequence of tokens and failing to capture the deeper discourse-…
arXiv:2604.22199v1 Announce Type: cross Abstract: Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. However, existing approaches often rely on repeated large-language-model (LLM) intera…
arXiv:2601.11020v3 Announce Type: replace Abstract: Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving information from the context. However, the role of these retrieval heads in improvin…
arXiv:2604.22294v1 Announce Type: new Abstract: Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections g…
We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The approach is scalable in production and reaches selective automation within two weeks for a new process, leveraging supervision al…
Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each document. However, any fixed LLM context window can be exceeded as document collections grow. A common workaround is to decompose documen…
Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. However, existing approaches often rely on repeated large-language-model (LLM) interaction for uncovered tasks, and even successful exe…
Large Language Models (LLMs) have shown immense potential in Knowledge Graph Completion (KGC), yet bridging the modality gap between continuous graph embeddings and discrete LLM tokens remains a critical challenge. While recent quantization-based approaches attempt to align these…
Large Language Models (LLMs) have shown immense potential in Knowledge Graph Completion (KGC), yet bridging the modality gap between continuous graph embeddings and discrete LLM tokens remains a critical challenge. While recent quantization-based approaches attempt to align these…
LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's memory footprint, thus motivating parameter-efficient a…
LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets. However, many applications of interest such as edge and on-device deployment are further constrained by the model's memory footprint, thus motivating parameter-efficient a…
Online reviews have played a pivotal role in consumers' decision-making processes. Existing research has highlighted the significant impact of managerial review responses on customer relationship management and firm performance. However, a large portion of online reviews remains …
Online reviews have played a pivotal role in consumers' decision-making processes. Existing research has highlighted the significant impact of managerial review responses on customer relationship management and firm performance. However, a large portion of online reviews remains …
In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In this approach, a reason generator first derives a ``reason'' for a user using his/her past education and career history. The reason s…
In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In this approach, a reason generator first derives a `"reason'' for a user using his/her past education and career history. The reason s…
arXiv cs.CV
TIER_1English(EN)·Md Adnan Arefeen, Biplob Debnath, Ravi K. Rajendran, Murugan Sankaradas, Srimat T. Chakradhar·
arXiv:2605.05344v1 Announce Type: new Abstract: In satellite applications, user queries often take the form of open-ended natural language, extending beyond a fixed set of predefined categories. This open-vocabulary nature poses significant challenges for retrieving relevant imag…
arXiv cs.CV
TIER_1English(EN)·Bumjun Kim, Albert No·
arXiv:2605.02908v1 Announce Type: new Abstract: Understanding how textual embeddings contribute to memorization in text-to-image diffusion models is crucial for both interpretability and safety. This paper investigates an unexpected behavior of CLIP embeddings in Stable Diffusion…
arXiv cs.CV
TIER_1English(EN)·Ruichi Zhang, Chikai Shang, Jiacheng Yang, Mengke Li, Yang Zhou, Junlong Gao, Yang Lu·
arXiv:2605.01309v1 Announce Type: new Abstract: Long-tailed distributions are common in real-world recognition tasks, where a few head classes have many samples while most tail classes have very few. Recently, fine-tuning foundation models for long-tailed learning has gained atte…
arXiv:2604.28095v1 Announce Type: new Abstract: Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition re…
arXiv:2604.27733v1 Announce Type: cross Abstract: Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as proxies for the intractable pair…
Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions. Moreover, small-lesion cues can be dilute…
Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as proxies for the intractable pairwise ranking loss. However, we demonstrate that fo…
arXiv:2604.25310v1 Announce Type: new Abstract: This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure times, which …
arXiv:2604.24952v1 Announce Type: new Abstract: Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: imag…
This work addresses the critical problem of tracking fast-moving objects through strongly scattering media in a low-light environment. Different from existing approaches that use frame-based cameras with fixed exposure times, which trade off signal-to-noise ratio for temporal res…
arXiv:2604.23788v1 Announce Type: new Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangement. We present MIRAGE, an evidence-centric framework designed to scaffold the ex…
arXiv:2404.10141v2 Announce Type: replace Abstract: Text-to-image (T2I) models have achieved remarkable progress in high-quality image synthesis, yet most benchmarks rely on simple, self-contained prompts, failing to capture the complexity of real-world captions. Human-written ca…
arXiv cs.CV
TIER_1English(EN)·Yifan Du, Zikang Liu, Jinbiao Peng, Jie Wu, Junyi Li, Jinyang Li, Wayne Xin Zhao, Ji-Rong Wen·
arXiv:2604.12890v2 Announce Type: replace Abstract: Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high token costs associated with multim…
arXiv:2604.23688v1 Announce Type: new Abstract: Proactive defense methods protect portrait images from unauthorized editing or talking face generation (TFG) by introducing pixel-level protective perturbations, and have already attracted increasing attention for privacy protection…
Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide only single, holistic annotations, resulting in severe label noise: images that excel in some dimensions but are deficie…
arXiv:2602.21977v4 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant culture of model sharing and c…
**Context Engineering** emerges as a significant trend in AI, highlighted by experts like **Andrej Karpathy**, **Walden Yan** from **Cognition**, and **Tobi Lutke**. It involves managing an LLM's context window with the right mix of prompts, retrieval, tools, and state to optimiz…
