Benchmarks, datasets, training techniques and the papers pushing the state of the art. Updated continuously from 20+ curated sources.
Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical systems. In practice, though, it can often be computationally challenging to establish when two system…
Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We…
Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, object state, sound, and touch evolve together as humans pursue goal…
We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel…
We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmenta…
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and A…
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regula…
Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibitive. We introduce Chimera, a hybrid visual diffusion backbone with…
Computer-using agents (CUAs) are advancing rapidly across the digital world. A CUA trajectory records the agent's actions, states, and reasoning. Verifying whether it fulfilled the task instruction is central to CUA eva…
Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups. Audit pipelines have been proposed to catch this, but their components are r…
Aligning large language models to prevent them attributing consciousness to themselves inadvertently alters their representations of mindedness in other entities alongside human beliefs and values. We demonstrate that s…
The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather than merely equipping them with a sophisticated yet inefficient reason…
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and…
Multimodal on-policy distillation (OPD) transfers fine-grained visual knowledge by supervising student-generated trajectories with a privileged-view teacher. Yet its next-token corrections are source-mixed, combining vi…
Post-training quantization (PTQ) has emerged as an effective solution for deploying Vision Transformers (ViTs) on resource-constrained devices. However, existing PTQ methods typically employ uniform bit-widths across tr…
SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeline: each PR (Pull Request) is paired with its linked issue by extracting issu…
On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reliably often requires substantial engineering effort. We identify a s…
High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs. This paradigm typically requires learning geometry from scratch and overlooks the rich s…
While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, w…
Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a sin…
We study the computational complexity of winner determination problems in approval-based committee elections under Thiele voting rules. These form a class of rules parameterized by a fixed weight vector that specifies h…
Deploying autonomous computer-use agents (CUAs) locally is increasingly important for privacy, cost efficiency, and practical usability, yet improving their performance under strict hardware constraints remains challeng…
Operational Earth observation increasingly calls for answering queries such as ``find the image pairs where a new building appeared.'' This means searching an archive of before-and-after (bi-temporal) satellite image pa…
Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We intro…
Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and image-derived summaries measured at unequal and informative times. Standa…
Medical image fusion aims to integrate complementary information from diverse imaging modalities to support clinical diagnosis. Existing methods typically apply uniform fusion rules globally, lacking a deep understandin…
Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery. While flow-matching models (, FlowDPO) have recently shown promise in this domain, their performance relies…
Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing…
Classifying pathological scars from clinical photographs requires distinguishing keloids from hypertrophic scars despite limited expert-labeled data and substantial acquisition variation across hospitals. End-to-end ima…
Metallic magnets exhibit complex spin dynamics governed by electronically generated interactions. Predictive simulations of such dynamics typically require repeated solutions of an underlying electronic problem througho…
Clustered Federated Learning (CFL) addresses data heterogeneity in federated settings by grouping clients with similar data distributions to enable effective training. Existing methods face a trade-off between privacy p…
On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning. Perception Success Rate…
LLM agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate att…
Fractional flow reserve derived from CT angiography (FFR-CT) simulates flow through a patient-specific vessel model, so its accuracy depends on the connectedness of the segmented tree, not only on volumetric overlap: a…
Quality metrics play a crucial role in the proper use of dimensionality reduction projections for visual analysis of high-dimensional data. They quantify the degree of distortion of a projection compared to the high-dim…
Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotemporal heterogeneity: different regions follow distinct temporal act…
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical valida…
Multimodal large language models (MLLMs) are increasingly used to analyze pathology images. However, dominant multimodal benchmarks in pathology mainly score final diagnostic answers, captions, or reports. These evaluat…
A single human must audit $N$ LLM agents under a budget of $B \ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy…
Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to token importanc…
Query optimization of Basic Graph Patterns (BGP) SPARQL queries over Knowledge Graphs (KG) requires accurate cardinality estimation. Recently published learned estimators outperform statistics- and sampling-based approa…
Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions. Existing e…
Microservice architectures have become dominant for modernizing monolithic systems, yet identifying appropriate services remains challenging and largely manual. Existing decomposition approaches are predominantly code-c…
Recent incidents of accidental damage and suspected sabotage to submarine telecommunication and power cables, particularly in the Baltic Sea, have underscored their vulnerability and the need for continuous monitoring s…
Machine learning is transforming molecular sciences by accelerating property prediction, simulation, and the discovery of new molecules and materials. Acquiring labeled data in these domains is often costly and time-con…
Supervised fine-tuning (SFT) can equip large language models (LLMs) with domain knowledge for high-performance computing (HPC) tasks such as data race detection and benchmark question answering. However, knowledge alone…
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gaus…
While depth sensors have the potential to complement RGB data for affordance segmentation in wearable robots, their usage seems to remain underexplored. The paper proposes two approaches: a reformulated version of hardw…
Large Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as market conditions, regulations, and corporate facts change continuously. While 4-bit qua…
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We form…
Monocular depth estimation (MDE) faces challenges with non-Lambertian surfaces and adverse weather conditions due to the visual ambiguities inherent in single-image limited information. Existing works address them in is…
Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive. Existing automated metrics often fail to capture the complexity and variability inher…
Hyperspectral imaging is widely used in remote sensing and engineering. Therefore, research on its classification methods is crucial. While CNN and Transformer-based methods have advanced, they still face locality const…
Modern Greek is a richly inflected language, yet the language models built for it are evaluated mainly on factual knowledge, and no benchmark is dedicated to their inflectional competence. We introduce MORFES (Morpholog…
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as static records to be replayed verbatim, inje…
Migration of legacy COBOL programs to Java requires extensive testing to ensure correct functionality. This effort is often complicated by the lack of test data and the difficulty of validating all corner cases. In this…
The deployment of Vision-Language Models (VLMs) in critical domains like disaster management requires high-quality multimodal datasets, especially for transferring knowledge via Data-Free Knowledge Distillation (DFKD).…
Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end…
Transformer depth is not used uniformly: lower and middle layers build semantic representations, while upper layers increasingly specialize them for prediction. We turn this division of labor into CoMem (Comprehension M…
Video re-shooting aims to regenerate videos with controllable camera motion and viewpoint. Existing methods rely on explicit 3D priors, which are limited by reconstruction quality and often perform poorly when synthesiz…
The one story that matters, 5 headlines and the paper everyone's citing — every Tuesday, free.
Subscribe free