The paper introduces CLUE, a contrastive learning framework that automates event type induction, naming, and annotation without relying on domain experts. It proposes a joint embedding representation that captures both verb-centric and semantic aspects of events, and uses contrastive loss–guided clustering to induce event types. The framework also includes a method for refining and naming the induced event types, and experimental results demonstrate its effectiveness.
By Pratik Maitra, Lauren Kwon, Qi Li
Neural Voxel Dynamics introduces a self‑supervised framework that learns 3D latent dynamics from monocular video by unprojecting V‑JEPAs features into a voxel grid using depth priors. It then applies Volumetric Feature Advection, an action‑conditioned transition model, to predict the evolution of these latent features directly in 3D, without relying on privileged physics‑engine states. The method is evaluated on synthetic and real datasets, demonstrating predictive fidelity, 3D geometric consistency, and physical plausibility via Physics‑IQ metrics.
By Zican Wang, Niloy Mitra
The paper "Can Language Models Play the Wikipedia Game?" investigates how language models perform on an information‑retrieval task where players navigate from one Wikipedia article to a target using only article links. The authors compare sentence‑embedding models and large language models across five Wikipedia languages and five academic‑literature datasets, building extensive local graphs of Wikipedia pages and paper citations with OpenAlex. They benchmark these models against human and TF‑IDF baselines, finding that no model significantly outperforms humans, though the best models (GPT‑o3 mini, GPT‑4o, QwQ:32B, and DeepSeek‑R1:70B) achieve comparable success, with performance varying by language and topic.
By Alexander Hickey, Joanna Knight, James Bishop
KV-Repurpose is an open‑source, vLLM‑based system that enables segment‑wise KV‑cache reuse beyond exact prompt prefixes in large language model serving. It integrates cache‑aware segment scheduling, prompt construction, capacity management, workload generation, and runtime monitoring. Experiments show that while naive segment reuse maintains output quality for single‑document tasks, it reveals limitations in cross‑document reasoning, and under a Zipfian RAG‑style workload it achieves a 63.9% token‑level cache hit rate versus 3.3% for prefix caching at 30 GB, dramatically lowering time‑to‑first‑token.
CliQ‑RRG is a two‑stage framework for generating radiology reports that aligns visual and textual data using disease‑aware embeddings and a Prior‑Guided Attention Module to capture multi‑view dependencies. In the second stage, GraphRAG‑guided retrieval adds graph‑grounded clinical evidence, and a large language model restructures the content into concise question‑answer pairs with diagnostic summaries. Experiments on two chest X‑ray benchmarks show that CliQ‑RRG outperforms previous methods in both lexical and clinical metrics, producing accurate and clinically coherent QA‑style reports.
The paper introduces Uni-DSM, a unified score-driven framework that uses denoising score matching to model video anomaly patterns for both detection and anticipation. It employs a shared noise-conditioned score transformer backbone with scene-dependent embeddings and motion-aware weighting, and differentiates between VAD and VAA through autoregressive denoising and a self-distilled denoising mechanism. Experiments on multiple benchmarks show state‑of‑the‑art performance for both tasks while maintaining high efficiency.
By Congqi Cao, Zhenhe Liang, Hanwen Zhang, Yifan Zhao, Qinyi Lv, Lingtong Min, Yanning Zhang
GLM-RAG introduces a graph language model (GLM) based retriever for retrieval‑augmented generation over knowledge graphs. The study compares GLM‑based, graph neural network (GNN)‑based, and vector‑search retrievers across single‑ and multi‑hop settings, emphasizing transferability to unseen domains. Results show that finetuned GLM retrievers achieve state‑of‑the‑art performance on two multi‑hop benchmarks and generalize better out of domain, while GNN retrievers excel at graph coverage and vector‑search performs best on single‑hop tasks.
By Maya Arseven, Anette Frank, Beni Egressy, Johann Higl, Moritz Plenz
SkillContrast is a training‑free selector that compares retrieved agent skills and keeps only the text that differs between them, preserving local context for a pretrained reranker. In experiments on 1,235 requests from SameCapRisk‑Bench, it improves clean‑hit rates by 54–72 over TF‑IDF query selection while using 51.1–58.8% fewer input tokens. The method shows that retaining differing text, rather than full skill bodies, is the key factor for better reranking performance.
By Jiandong Ding, Honglei Ji, Ming Liu, Tao Duan
The study examined whether ultra‑brief naturalistic concern text could complement wearable sensor data for monitoring student health. Over a year, 458 university students provided three‑word responses to a bi‑monthly prompt while wearing Oura rings, and the researchers compared different NLP methods to link these brief texts to nine sleep and physical activity outcomes. Findings indicated that weeks with academic‑concern framing correlated with lower physical activity, while emotional exhaustion language correlated with poorer sleep quality and lower heart rate variability, suggesting that affective content may add value to passive physiological monitoring.
By Tamunotonye Harry, Johanna Hidalgo, Matthew Price, Yuanyuan Feng, Kathryn Stanton, Connie Tompkins, Peter Sheridan Dodds, Mikaela Irene Fudolig, Laura Bloomfield, Christopher Danforth
Chronos is a test‑time framework that transforms historical pull requests into structured experience cards linked by a typed graph of code, developer intent, and organizational relations. It uses semantic search and weighted multi‑hop expansion to retrieve relevant cards, guiding both patch generation and selection by LLM‑based code agents. The approach improves resolution rates across multiple LLM backbones on SWE‑Bench and related benchmarks, and human evaluation shows a higher number of useful cards retrieved compared to flat semantic retrieval.
By Xin Yin, Yiang Zhang, Zhiyuan Peng, Chao Ni, Zhe Cui, Xiaohua Xin
NativeScope is a retrieval method that first scopes candidate text chunks using a known anchor and a relation (such as belonging, before, or after) and then ranks only those chunks that overlap the selected scope. In experiments on 200 controlled documents and memory records, NativeScope achieved 89.28 % recall for documents and 72.50 % for memories, outperforming instance‑wide Dense RAG by 42.75 and 22.00 percentage points. An internal variant, NS‑FullQ, which ranks candidates with the full question, showed similar performance, indicating that the primary benefit comes from relational scoping rather than query length.
whyItMatters: The study demonstrates that incorporating native structural relations into retrieval can substantially improve recall, especially when anchor coordinates and relations are reliable.
By Long Wang
The paper introduces RAG-E, an explainability framework for Retrieval-Augmented Generation (RAG) systems that quantifies how well a language model’s document usage aligns with the retriever’s rankings. It adapts Integrated Gradients for retriever analysis, uses a Monte Carlo‑stabilized Shapley Value approximation for generator attribution, and proposes the Weighted Alignment between Retriever and Generator (WARG) metric. Experiments on PopQA, QAMPARI, and TREC CAST show that generators often ignore top‑ranked documents, and WARG outperforms Pearson and Spearman correlations in measuring alignment, offering a practical tool for auditing RAG performance.
By Korbinian Randl, Guido Rocchietti, Aron Henriksson, Ziawasch Abedjan, Tony Lindgren, John Pavlopoulos
The paper proposes a multilingual adaptation of an English quality classifier to select high‑quality training data for large language model pretraining across more than 100 languages. The method trains a small multi‑layer perceptron on Transformer embeddings, using machine‑translated text scored by the English classifier as labels. Experiments on 1B, 3B, and 8B parameter models show that the adapted classifier preserves benchmark performance and regional knowledge, and it generalizes to unseen languages by learning the original scoring criteria.
By Vinko Sabol\v{c}ec, Bettina Messmer, Yassine Turki, Martin Jaggi
The paper investigates why visual instance retrieval often fails when the same object appears at different apparent sizes in query and gallery images. It identifies object-to-image (O2I) ratio mismatch—where the object occupies different fractions of the two images—as the dominant cause of performance degradation, rather than resolution loss. Experiments on a controlled benchmark with 3,021 Objaverse objects show that over 80% of cross-distance degradation is due to O2I mismatch for most pretrained backbones, and that multi-scale architectures only reduce resolution effects but remain vulnerable to O2I mismatch. The authors demonstrate that query-side scale augmentation and an OWLv2 crop reranker achieve state‑of‑the‑art results on ILIAS 100M without retraining the gallery, and that a LoRA fine‑tune can match these gains in a single forward pass, indicating that O2I robustness can be learned.
By Boaz Meivar, Ofir Kedem, Amit Edenzon, Gal Chechik, Shai Avidan
MA-JEPA is a stochastic world model designed for multi‑agent reinforcement learning that replaces observation reconstruction with joint‑embedding prediction. It uses a categorical latent state and a causal Transformer trained on posterior and action‑conditioned dynamics to generate imagined trajectories for actor‑critic learning. The model achieves strong performance on the SMAC benchmark, matching or surpassing the best reported mean win rates on half of the evaluated maps.
By Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de Witt
DaCe-DT is an offline multi‑task reinforcement learning framework that tackles data‑level bottlenecks by introducing length‑gated prompt masking, retrieval‑augmented prompt construction, and value‑adaptive return calibration. These mechanisms adapt prompts to diverse task complexities, ensure semantic relevance of prompt segments, and correct misleading supervision from fragmented trajectories. Experiments on Meta‑World show that DaCe‑DT outperforms state‑of‑the‑art methods, improving performance by 11.73% on optimal datasets and 13.34% on suboptimal datasets.
By Xinfei Wang, Shanchen Pang, Chenhao Zhang, Shudong Wang, Wenhao Ji, Haiyuan Gui, Meng Han, Xiaojian Liao
The paper evaluates EEG foundation models (EEG‑FMs) beyond clean accuracy, testing six models and a supervised baseline across ten datasets. It finds that no single model excels in all robustness tests, that attribution methods reveal task‑appropriate brain region relevance, and that poor head‑only performance is largely due to pooling strategies rather than representation quality. The study also shows that fine‑tuning repurposes late blocks while early blocks already encode task information.
By Urban \v{S}irca, Maryam Alimardani, Stefanos Zafeiriou, Konstantinos Barmpas
The paper introduces SCION, a single-model framework that jointly learns generative and self‑supervised representation tasks without relying on labels or pretrained encoders. SCION uses a pixel‑space encoder conditioned on a flow timestep and a shared embedding, training contrastive and flow‑matching objectives simultaneously with gradient‑norm balancing and stop‑gradient techniques. On ImageNet 256×256, SCION achieves state‑of‑the‑art FID scores (8.92 with JiT‑B and 5.89/3.47 with JiT‑L) surpassing prior class‑unconditional and pretrained‑conditioned methods.
By Vicente Balmaseda, Ching-Long Lin, Tianbao Yang
SplitJEPA is a new joint embedding predictive architecture that learns a latent state and its invariant and variant components directly in representation space, without reconstructing observations. The method proves that, under stationary Gaussian predictive dynamics and a full‑rank variation condition, it can identify the invariant and variant subspaces up to independent block‑wise isometries. Experiments on synthetic nonlinear systems and robotic manipulation tasks confirm the theoretical guarantees and demonstrate practical benefits for robustness and efficiency.
By Ruijin Hua, Zichuan Liu, Zhuokai Zhao, Yujia Zheng
PathLang is a new, language‑centered benchmark for vision‑language models in computational pathology. It keeps the underlying pathology slides, ground‑truth labels, and image‑text evaluation direction constant while systematically varying the diagnostic language used in prompts, reflecting how pathologists actually rephrase diagnoses. The benchmark covers four task families—zero‑shot classification with image‑text alignment, cross‑modal retrieval, paraphrase robustness, and open‑vocabulary diagnosis retrieval—and evaluates nine VLMs across five public datasets spanning four organs.
By Fanqi Cheng, Kuo Gong, Shangke Liu, Beidi Zhao, Junchao Zhu, Zheyu Zhu, Leiyue Zhao, Fengbei Liu, John Cannon, Gang Wang, Zu-hua Gao, Kenji Ikemura, Yihe Yang, Yaohong Wang, Yuankai Huo, Xiaoxiao Li, Mert R. Sabuncu, Ruining Deng