Search: “reasoning”

arXiv:2608.29278v1 Announce Type: new Abstract: Omni-modal large language models are increasingly evaluated on clean text--vision--audio inputs, where every channel is present, synchronized, and readi

arXiv:2608.26355v1 Announce Type: new Abstract: While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often f

arXiv:2608.26866v1 Announce Type: new Abstract: Many multimodal tasks depend on how visual elements are ordered and composed, not only on recognizing them in isolation. Internet memes are a compact ca

arXiv:2510.22775v2 Announce Type: replace Abstract: While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. Th

arXiv:2608.26036v1 Announce Type: cross Abstract: Answer accuracy is an insufficient reliability signal for LLM data agents. In structured-data tasks, a benchmark-correct answer can be produced by an

arXiv:2608.24535v1 Announce Type: new Abstract: Data visualizations are widely used for communicating information, but they are also vulnerable to intentional manipulations that induce misleading inte

arXiv:2608.22753v1 Announce Type: new Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided procedu

arXiv:2608.21431v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information.

arXiv:2608.23152v1 Announce Type: new Abstract: Counterspeech effectively neutralizes the impact of online hate. Although prior work explores automated counterspeech generation, it largely emphasizes

arXiv:2608.22479v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) enables LLMs to access external knowledge for answering knowledge-intensive questions. For complex multi-hop questi

arXiv:2608.23061v1 Announce Type: new Abstract: Background: Automating clinical guideline-based decision-making with large language models (LLMs) remains challenging because of reliability, hallucinat

arXiv:2608.22128v1 Announce Type: new Abstract: Printability assessment in additive manufacturing is typically conducted at the geometry level before printing to determine whether a computer-aided des

arXiv:2608.22584v1 Announce Type: new Abstract: Two-stage neuro-symbolic architectures provide an elegant paradigm for visual problem solving by cleanly separating connectionist perception of predefin

arXiv:2608.21032v1 Announce Type: new Abstract: Vehicle-to-Everything (V2X) cooperation enables beyond-line-of-sight perception, mitigating occlusions in single-vehicle sensing. However, existing V2X

arXiv:2607.17417v2 Announce Type: replace Abstract: Language models are moving into chemistry and materials discovery workflows, where a wrong molecular formula, space group, or formation energy can s

arXiv:2608.18575v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outco

arXiv:2608.17151v1 Announce Type: new Abstract: Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context

arXiv:2608.16103v1 Announce Type: new Abstract: Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form lang

arXiv:2508.08879v3 Announce Type: replace-cross Abstract: The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of models' hidden

arXiv:2509.06461v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visu

arXiv:2608.14804v1 Announce Type: new Abstract: Large language models (LLMs) have become the dominant interface of clinical artificial intelligence, yet the interface they expose (text in, text out, o

arXiv:2608.16776v1 Announce Type: new Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irre

arXiv:2608.14566v1 Announce Type: new Abstract: Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily on what we call the moral value problem, i.e., whet

arXiv:2608.15291v1 Announce Type: new Abstract: Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while

arXiv:2602.21219v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, re

arXiv:2507.20776v3 Announce Type: replace Abstract: Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging p

arXiv:2608.16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question formulations without task-specific training. Howev

arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently beni

arXiv:2608.12836v1 Announce Type: cross Abstract: Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the ind

arXiv:2602.14098v2 Announce Type: replace Abstract: Existing Multimodal Large Language Models (MLLMs) for image forgery detection and localization predominantly operate under a text-centric Chain-of-T

arXiv:2608.11739v1 Announce Type: cross Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This mak

arXiv:2608.11573v1 Announce Type: cross Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LL

arXiv:2608.10438v1 Announce Type: new Abstract: Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. Fo

arXiv:2608.10908v1 Announce Type: cross Abstract: As generative multimedia evolves from static image synthesis to complex, interleaved visual narratives, a foundational bottleneck has emerged: the jud

arXiv:2608.10740v1 Announce Type: new Abstract: Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the l

arXiv:2608.08061v1 Announce Type: new Abstract: The key question in moral judgement is not simply whether someone chooses the 'right' answer, but how they decide what matters most when moral principle

arXiv:2608.09053v1 Announce Type: cross Abstract: Cardiologists interpret electrocardiograms by localizing waveform components, measuring rhythm and interval patterns, and translating these structured

arXiv:2602.23290v2 Announce Type: replace Abstract: Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompo

arXiv:2608.09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet exi

arXiv:2608.08053v1 Announce Type: cross Abstract: Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model t

arXiv:2510.22087v3 Announce Type: replace-cross Abstract: The field of computer architecture, which bridges high-level software abstractions and low-level hardware implementations, remains absent from

arXiv:2608.09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring and imp

arXiv:2608.07994v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documen

arXiv:2608.07004v1 Announce Type: new Abstract: Although remarkable capabilities have been demonstrated by Large Language Models (LLMs) across scientific domains, feedback controller design remains un

arXiv:2608.06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits

arXiv:2608.05254v1 Announce Type: new Abstract: Large language models can derive a plausible mathematical object yet still violate explicit requirements--for example, by omitting a modular reduction,