Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into $K$ representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training as a merge prior to discourage cross-instance mixing, requires no ground-truth bounding boxes or detectors at inference time, and adapts only the shared projection layer with frozen vision and language backbones. With $K=64$, SaMer removes more than 93% of image-side tokens and reduces ColPali storage by $16.09\times$, while improving R@1 on Flickr30K and MSCOCO. These gains arise because object-aware merging preserves query-selectable object evidence that pruning or feature-only pooling can remove or collapse. SaMer also outperforms compression baselines and shows stronger phrase-level grounding, suggesting that efficient multi-vector retrieval depends not only on reducing token count, but on preserving the evidence future query tokens need to select.
Suhyeong Park, Junha Jung, Jungwoo Park et al.· 1 citation
Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations.Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior.However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.
E. Herrewijnen, Benedetta Muscato, Gizem Gezici et al.· 0 citations
We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a large language model (LLM). GPTKB 2.0 contains 38.4M triples over 1.6M canonical entities, together with 207.6K consolidated relations and 66K consolidated classes. Unlike prior LLM-derived knowledge bases that largely identify entities by surface strings, GPTKB 2.0 performs context-guided disambiguation during recursive KB construction, separating homonyms and merging synonymous mentions as facts are elicited. The demo makes this process inspectable: users can browse entities, follow links across the KB, and audit the provenance of individual facts, including surface forms, candidate matches, source triples, and disambiguation decisions. The interface further supports structured SPARQL queries, natural-language questions translated to SPARQL, and entity linking from user-provided text to canonical GPTKB 2.0 entries. GPTKB 2.0 is available at https://gptkb.org/, with the full KB downloadable for offline use.
Yujia Hu, Tuan-Phong Nguyen, S. Razniewski· 0 citations
We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a budget of at most 32B parameters and no model fine-tuning. Our system combines structured chain-of-thought reasoning, relation-specific query strategies, and a reasoning-based empty-set gate to elicit parametric knowledge, followed by direct extraction into valid JSON arrays. On the test set, the system, built on the Mistral-Small-24B-Instruct-2501 model, achieves a macro-F1 score of 0.62, with particularly strong results on countryLandBordersCountry (F1 = 0.95), companyTradesAtStockExchange (F1 = 0.73), and hasArea (F1 = 0.77). Our code is publicly available at https://github.com/yammdd/AKBC-Shared-Task-2026.
T. Bùi, T. Do, Tuan-Phong Nguyen· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce \textbf{DiaLLM}, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model alignment strategies, giving the first controlled comparison of these components across Australian, Indian, and Northern British English. Our results reveal that dialectal robustness and generation are \emph{dissociated}: benchmarks are shaped by continual pretraining and SFT, while alignment visibly reshapes generation in ways benchmarks do not capture. Explicit variety-targeted adaptation produces output reliably recognised as dialectal and preferred over broad alignment, yet the method that most aggressively optimises the dialectal reward is not preferred by human evaluators. Independent linguistic analysis corroborates this reward-quality gap, most clearly on two of the three families. No single alignment method dominates, and closing the gap will require richer reward designs and continued investment in dialectal resources. We release all code, checkpoints, and preference datasets.
Jordan Painter, Dipankar Srirag, Adarsh Kappiyath et al.· 1 citation· ⚡1
PepBAN is introduced, a deep learning framework for modeling PepPI predictions that effectively learns the pattern of pairwise local interactions, enables the identification of key residues participating in the peptide-protein interactions, and offers an intuitive approach to interpret the underlying mechanisms of PepPIs via analyzing attention weights.
Shuaiyan Li, Xiaorui Wang, Yuchen Zhu et al.· Journal of Chemical Informat...· 4 citations
PepPCBench enables a robust evaluation of PFNN-based methods and supports their continued development for peptide-protein structure prediction, and highlights the influence of peptide length, conformational flexibility, and training set similarity on prediction accuracy.
Si-Long Zhai, Huifeng Zhao, Ji-Ke Wang et al.· Journal of Chemical Informat...· 13 citations· ⚡1
A unified benchmarking framework is established that enables systematic evaluation of docking methods across diverse tasks and provides critical insights into the strengths and limitations of current docking strategies, thereby informing future developments in protein-protein docking research.
Linlong Jiang, Ke Zhang, Kai Zhu et al.· Journal of Chemical Informat...· 3 citations
These results suggest that it will be much time-saving to utilize RAMD with high random force for interaction pathway exploration for both the pathway obvious and unobvious systems if the protein keeps stable in the simulation if the protein keeps stable in the simulation.
Zhiliang Jiang, Mingyun Shen, Zhe Wang et al.· Journal of Chemical Physics· 1 citation
This study leverages an integrated computational strategy combining molecular dynamics simulation, end-point binding free-energy calculation, and enhanced sampling technologies to elucidate the dynamic characteristics of RAS-ligand-CYPA interactions and uncover the dynamic process of stabilizer-mediated KRAS-CYPA stabilization.
Kexin Xu, Mingyun Shen, Zhe Wang et al.· Journal of Chemical Informat...· 0 citations
This Account describes a computational and AI-driven ecosystem for structure-based covalent drug discovery and dives into a suite of cutting-edge, AI-driven computational methods, exploring the potential of deep learning in tasks such as molecular docking, covalent binding site prediction, and lead optimization.
Shi Li, Hongyan Du, Xujun Zhang et al.· Accounts of Chemical Researc...· 4 citations
The DRHIN platform provides a code-free portal supporting three key predictive tasks: discovering drug-disease associations, repurposing existing drugs for new indications, and identifying potential therapies for specific diseases, making analyses accessible and reproducible.
Bowei Zhao, Dongxu Li, Yue Yang et al.· Journal of Chemical Informat...· 10 citations· ⚡1
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
