중동전쟁 여파…기관 외화증권 5천억달러 돌파 후 첫 감소
한겨레·
(서울=연합뉴스) 고은지 기자 = 유안타증권[003470]은 3개월간 단독 판매한 iM에셋 히어로 셀렉션 증권투자신탁(사모투자재간접형) 판매...
(서울=연합뉴스) 정수연 기자 = SSG닷컴은 명품 브랜드 미우미우(Miu Miu) 공식 스토어를 오픈했다고 1일 밝혔다.
(서울=연합뉴스) 강수련 기자 = DB생명은 업계 최초로 인공지능(AI) 기반 대화형 헬스케어 서비스를 탑재한 (무)AI 라이프케어 정기보험 ...
콩고민주공화국에서 현재까지 명확한 백신이나 치료제가 없는 분디부교형 에볼라 바이러스가 확산 중인 가운데 일부 환자들이 회복되는 경우가 처음으로 …
[고척=스포츠조선 김영록 기자] "이 안타로, 주루사만 나오지 않는다면…" 대체 왜 뛰었을까. KBO리그 전체로 따져도 8년만의 대기록 도전이 허무하게 무산됐다. 생애 최고의 한달을 보내던 동료는 도전할 기회조차 놓쳐버렸다. 잘못된 선택 하나가 지켜보던 모든 이들의 탄식을 불렀다. 지난달 31일 고척스카이돔. KT 위즈와 키움 히어로즈의 주말시리즈 3차전.
[OSEN=우충원 기자] 또다시 ‘아시안 패싱’ 논란이 고개를 들었다. 이번에는 이강인(PSG)이었다. 유럽 정상에 오른 순간에도 결정적인 장면이 중계 화면에 제대로 담기지 않으면서 팬들의 아쉬움과 의문이 동시에 커지고 있다.파리 생제르맹(PSG)은 지난달 31일(이하 한국시간) 헝가리 부다페스트 푸슈카시 아레나에서 열린 아스날과의 2025-2026시즌 유
[스포츠조선 노주환 기자]유럽 챔피언 파리생제르맹(PSG)이 선수 보강에 열을 올리고 있다. 그들은 본머스 영건 엘리 주니어 크루피(20)를 점찍은 것으로 보인다. 프랑스 매체 '레키프'는 유럽챔피언스리그 우승팀 PSG를 포함해 유럽의 거의 모든 최고 클럽들이 크루피를 예의주시하고 있다고 1일 보도했다. 이 매체는 "지난 몇 주 동안 파리생제르맹 구단 경영
(서울=연합뉴스) 차민지 기자 = 행정안전부는 제9회 전국동시지방선거를 맞아 우리나라 지방자치와 자치분권의 역사를 담은 대통령기록물 38건을 6...
(서울=연합뉴스) 성서호 기자 = 62세 김성호(가명) 씨는 어느 날 아침 오른손에 힘이 빠져 젓가락을 떨어뜨리고, 말이 어눌해져 인근의 한 2...
▲ 30일 서울 강북구 강북문화예술회관에에 마련된 사전투표소에서 유권자들이 투표를 하기 위해 대기해 있다.제9회 전국동시지방선거 사전…
(서울=연합뉴스) 최주성 기자 = 중앙선거관리위원회는 제9회 전국동시지방선거 사전투표 둘째 날인 30일 오후 3시 현재 투표율이 19.77%로 ...
(서울=연합뉴스) 이태수 기자 = 그룹 스트레이 키즈의 미로 (MIROH) 뮤직비디오 유튜브 조회 수가 2억건을 돌파했다고 소속사 JYP엔터테...
[대전=스포츠조선 이종서 기자] "첫 홈런을 쳤을 때는 드디어 나왔구나 생각이 들었는데…." 허인서(23·한화 이글스)는 29일 대전 한화생명볼파크에서 열린 SSG 랜더스와의 홈 경기에 포수 겸 6번타자로 선발 출전해 3타수 1안타(1홈런) 2타점 1득점을 기록했다. 두 팀의 선발이 팽팽하게 맞붙었던 경기. 한화 오웬 화이트와 SSG 최민준은 3회까지 퍼펙
[OSEN=창원, 조형래 기자] “쫄면 아무 것도 못하잖아요.”프로야구 한화 이글스 투수 박준영(24)은 지난해 드래프트 미지명의 아픔을 맛봤지만 육성선수로 입단, 올해 1군 데뷔전까지 초고속으로 치렀다. 그리고 모두가 깜짝 놀랄 만한 데뷔전과 두 번째 등판을 마쳤다. 퓨처스리그에서 7경기 4승 평균자책점 1.29(28이닝 4자책점)의 기록을 남기며 무력시
Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. We therefore propose Lumos-Nexus, a training-efficient unified video generation framework that facilitates the development of strong reasoning-driven generation capabilities while significantly enhancing visual fidelity. Lumos-Nexus adopts
Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection, attackers frequently distribute their misuse, splitting a harmful task across many user accounts so each individual transcript looks benign. Because safety monitors score only one agent context at a time, they are structurally blind to misuse that is only visible in aggregate, across many accounts. We show this gap is real by building, to our know
Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this finding, we present TunerDiT, a simple yet effective progressive steering method that requires no ad
Grasping the semantics of rare constructions (form-meaning pairings) has been shown to be a challenging problem that has currently only been solved by the largest LLMs. It remains an open question if open-source models have robust constructional understanding, and if so, what learning dynamics underlie the acquisition of this knowledge. Focusing on a set of rare Paired-Focus constructions in English (e.g. "let alone", "much less"), we construct a novel dataset to test their meanings using both s
Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive distracting content. Reinforcement learning with verifiable rewards (RLVR) has shown promise for this task, yet existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals that cannot supervise intermediate reasoning steps. To address these issues, we introduce \textsc{LongTraceRL}. For data construction, we
The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that standard formalisms do not directly capture. We introduce context-dependent argumentation frameworks (CDAFs), an extension of Dung's theory in which a defeat function determines, per context, which attacks succeed. A perspective-labeled specialisation derives the defeat function from a relevance set $ρ$ and a priority $π$. The relevance set is the age
Scalable information retrieval testing needs corpora that are large enough to stress index construction, ranking latency, query routing, and evaluation tooling, yet human-judged test collections remain expensive and may be unavailable when documents are private or still under design. This paper introduces SPECTRA, a reproducible framework for generating synthetic text corpora and retrieval test collections through a separation of latent topical structure, surface text realization, metadata contr
We present the first systematic study of masked diffusion language models (MDLMs) for graph-to-text generation. We analyze MDLM generation trajectories -- the order in which tokens are unmasked during iterative decoding -- and find that, unlike autoregressive LLMs which generate text linearly, MDLMs naturally prioritize entities first, followed by relational and function words, with structural tokens resolved last. We further identify a previously undocumented failure mode of supervised fine-tun
Transformer-based language models are widespread in today's society. As such, understanding the mechanisms by which they solve structured tasks and predicting how they may behave in novel scenarios is of great importance for safe deployment. We study the learning dynamics of attention heads in a controlled setting by training a decoder-only Transformer (GPT-J) on two structurally equivalent multi-hop reasoning tasks: a number task requiring positional reasoning and a letter task requiring symbol
Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind) cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting ambiguous input images, with models collapsing to male even for strongly female-stereotyped occupations. But do these outputs re
Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering into a single backbone, turning self-supervised NVS into a well-posed single-model scaling problem. A minimal dynamic state
Three-dimensional scene reconstruction depends on local image evidence that is both visually discriminative and geometrically useful. Fixed feature thresholds and uniform feature budgets are easy to deploy, but they can waste computation on repeated texture, low-parallax regions, or unstable points. This paper proposes an adaptive feature-optimized vision front end for 3D reconstruction. The method scores candidate features by texture, repeatability, distinctiveness, expected triangulation angle
Credential leakage in public source code repositories poses a critical security threat, with over 23.8 million secrets exposed in 2024 alone. Existing detection tools suffer from high false-positive rates because rigid pattern matching and binary classification schemes fail to distinguish genuine credentials from placeholder or weak credentials. We propose a three-class classification framework that explicitly models placeholder or weak credentials as a distinct class, leveraging CodeBERT-based
Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows. However, many works within the field state emergence of, ascribe to, or assume, generalised anthropomorphic attributes to them (e.g., morality or understanding of natural language). Our goal is not to argue in favour or against the existence of these attributes, but to point out that these conclusions could be incorrect. For this we build and train a simple neural network on the videogame Age of
Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when their successful trajectories are structurally compressible, decomposed into a small set of reusable abstract patterns. To formalize this, we introduce ReuseRL, which grounds agentic RL in the Minimum Description Length (MDL) principle. ReuseRL extracts a shared skill dictionary from successful trajectories and augments the RL object
Graph Neural Networks (GNNs) are bottlenecked by sparse, irregular memory access. Popular frameworks such as DGL and PyTorch Geometric support general message passing, but complex layers often materialize edge-wise intermediates, increasing memory traffic and limiting scalability on large graphs. We take an I/O- and arithmetic-intensity--centric view and show that widely used layers fall into three kernel families: SpMM-based convolutions, reduction-based aggregations, and attention-based layers
Large language models (LLMs) often solve reasoning problems by generating intermediate traces that explore and revise partial solutions. From a search perspective, these traces can be viewed as linearized search trees, where the model extends a partial solution, abandons it when it fails, and backtracks to try alternatives. Compared with traditional heuristic-guided search, such a policy has a potential advantage: it conditions on the whole search trace rather than only on the current local stat
Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The BEA-Dialogue corpus addresses this need, but its strictly speaker-disjoint train/dev/eval split reduces the usable material to only 85 hours. In this paper, we introduce BEA-Dialogue+, an expanded version of the corpus that relaxes the split criterion for experimenters and dialogue partners while preserving complete separation of the primary speake
Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles. The rise of LLM-based scientific agents creates an opportunity to automate this process. Such a system must support the full research lifecycle, maintain structured persistent memory across projects, and improve its own research procedures over time. However, existing systems either partially satisfy or fail
GPU kernels are the workhorse of modern deep learning, and optimizing them (via evolutionary search or coding agents) usually requires repeated measurement on target hardware. While these measurements provide the ground-truth signal necessary for kernel search, they are costly, because each evaluation of a kernel requires compilation and repeated execution on a GPU. As improvements in LLM inference reduce the cost of writing novel kernels and LLM-driven searches scale to large search budgets, on
Mixture-of-Experts (MoE) has become the dominant architecture for frontier language models. To meet this demand, production frameworks have built optimized MoE training stacks over years of engineering effort. Yet evolving these stacks for new architectures and system optimizations remains expensive. With the rise of AI coding agents, they could automate parts of training-framework development and accelerate this evolution. But applying them to these existing frameworks carries hidden costs, inv
Aspect Sentiment Triplet Extraction (ASTE) aims to identify aspect terms, opinion terms, and sentiment polarities as structured triplets, providing essential inputs for downstream information system applications such as opinion mining, explainable recommendations, and review summarization. Prior work mainly focuses on end-to-end extraction, while post hoc verification of extracted triplets remains comparatively underexplored. This gap limits the reliability of ASTE systems, since predicted tripl
In this work we study agents in simulated bargaining scenarios, where a buyer and a seller communicate through a text channel and attempt to negotiate mutually beneficial trades, under different information regimes (complete information, information asymmetry or mutual uncertainty). We evaluate their performance w.r.t. game-theoretical solutions and further investigate their honesty (their tendency to disclose or withhold information or to mislead and deceive) as well as their credulity (their t
Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approximation are therefore essential. Relational Reinforcement Learning (RRL) offers a way to reason about objects and their relations, and the CARCASS framework by Martijn van Otterlo demonstrates how logical representations can model Markov Decision Processes (MDPs) in first-order do
Simultaneous speech-to-text translation (SimulST) generates translations while speech is still unfolding, requiring a streaming policy that decides when to read and when to write. State-of-the-art approaches rely on attention-based encoder-decoder models where cross-attention provides explicit alignment signals. In contrast, Speech Large Language Models (SpeechLLMs) are decoder-only architectures relying solely on self-attention. This raises a central question: whether decoder self-attention con
In this paper, we show the possibility of a direct injection of algorithms into neural network architecture. We focus on a complex algorithm, that is, Cocke-Youger-Kasami (CYK) for parsing context-free grammars in Chomsky Normal Form and we propose CYKNN, a simple recurrent neural network architecture for encoding the CYK algorithm in trainable matrix-vector multiplications.We experimented with a very simple grammar with 4 variations showing that our approach outperforms existing LLMs with more
Food-as-Medicine requires models to reason beyond what a dish is or what nutrition it contains: they must decide whether a concrete food choice is appropriate for a specific health condition. Existing food AI benchmarks primarily evaluate dish recognition, recipe understanding, nutrient estimation, or general nutrition question answering, leaving this health-aware decision layer largely untested. We introduce FAM-Bench, a multi-modal Food-as-Medicine benchmark with 2500 nutrition-expert-verified
Skill documents provide procedural knowledge to large-language-model agents at inference time. This article studies whether the presentation granularity of controlled skill knowledge changes downstream task success. The experiment uses a pinned SkillsBench version, a 30-task domain-balanced subset validated by official oracle runs, two reasoning-enabled model configurations, six skill conditions, and five trials per task-condition-model cell. Skill availability is the clearest empirical signal.
Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster maps) and translate them into textual descriptions as LLMs' inputs. However, the linguistic structures of such text-based spatial representations and the choices of contextual features (e.g., topology, geometry) they contain are often treated as neutral engineering decisions rather than key factors that shape LLMs' behavior. To fill the gap, we propos
Sign language translation (SLT) remains constrained by limited paired sign-video/text corpora and heavy-tailed target vocabularies. We study target-side augmentation in which GPT-4o generates controlled paraphrase variants of reference sentences while the sign input remains unchanged. A Signformer-style pose-based Transformer is trained under a two-stage schedule: pre-training on the augmented corpus followed by fine-tuning on the original references. We evaluate on three datasets spanning compl
Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-horizon inference loops, leading to high inference cost and limited suitability for time-sensitive news retrieval. We propose DynaTree, a two-stage framework for efficient and adaptive news retrieval. In the offline stage, DynaTree uses coordinated agents to construct a reusable ret