AI research papers
What AI researchers are reading: the papers the Hugging Face community picks each day, and new arXiv submissions in the directions we follow. Titles and abstracts are arXiv’s; every paper links to arXiv.
Where research is heading
- Vision & multimodal22% of papers in 14 days
- Agents19% of papers in 14 days · -21 pts vs 12 weeks before
- Efficiency17% of papers in 14 days
- Benchmarks & evals9% of papers in 14 days
- Reasoning7% of papers in 14 days
- Retrieval & RAG6% of papers in 14 days · -14 pts vs 12 weeks before
Medical Image Segmentation: Foundation Model Adaptation versus Task-Specific Training
Emre Kutlusan, Yongmin Li
Foundation models pretrained on large natural-image collections are increasingly adapted for medical image segmentation, in the expectation that they will replace models trained for each task. Most comparisons, however, use data from the training distribution and a single task-specific baseline whose configuration…
Toward Foundation Detection Models via Example-Based Grounding in EM-DETR
Sheethal Bhat, Bogdan Georgescu, Awais Mansoor et al.
DeepLearning (DL)-based Computer-Aided Diagnostic (CAD) systems have shown great promise in supporting clinicians, but their performance heavily depends on the availability of large, well-annotated datasets. In medical lesion detection, the scarcity of comprehensive, stan dardized annotations and the heterogeneity…
Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations
Ziang Liu, James J. Kim, Yijia Dai et al.
LLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternative the evidence…
Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents
Megha Srivastava, Michael H. Lim, Allison M. Keys et al.
Predicting how a ligand binds to its target is central to small-molecule drug discovery. Modern cofolding models can generate diverse candidate poses, but reliably ranking these candidates remains challenging. We introduce Pyrite, a pairwise pose-ranking benchmark comprising 1,500 pose pairs across diverse…
Continual-ARC: Measuring Skill Acquisition over a Working Lifetime
Daniel Lenton
Agent harnesses have emerged as a promising mechanism for continual learning, alongside test-time parametric learning. However, the current benchmarks have several limitations: they generally focus on a single applied domain, serve each instance only once, and assume a single family of learner, so memory-based and…
Emergent Biological Capabilities in a Foundation Model for Molecular Interactions
Adi Mashiach
Foundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-ligand sequences.…
Measuring Robustness and Efficiency in a Connectome-Constrained Fly Visual System Model: Linking an Adversarial and a Perceptual Illusion
Alexandre Garcia-Duran, Alejandro Rodriguez-Garcia, Manuel Molano-Mazón et al.
Biological visual systems compute reliably under tight metabolic and wiring constraints, whereas artificial vision systems consume far more energy and can be sensitive to adversarial perturbations. Whether networks with brain-like wiring are more robust at lower computational cost is unclear. We address this by…
RS-JEPA: Remote Sensing Joint-Embedding Predictive Architecture with Scan-Path Views for Cross-Sensor Image Retrieval
Tanishq Rachamalla, Srishti Kaushik, Muhammad Attique Khan et al.
Cross-sensor remote sensing image retrieval aims to find scenes with the same content across heterogeneous sensors, such as SAR and optical or panchromatic (PAN) and multispectral (MS) imagery, without manual labels. Existing self-supervised methods either reconstruct sensor-specific pixel detail, align each image…
Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents
Howard Zhang, Chuck Arvin, Logan Brown et al.
Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based LLM judging,…
ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows
Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya et al.
Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choose every step of every run, which adds latency and cost at scale. We present ReTrace, which turns…
Mechanistic Interpretability Needs a Logic of Inference
Zhimin Hu, Chen Jiang, Hanbo Xie et al.
Neural networks are increasingly studied not merely as predictive systems, but as complex systems whose internal computations are themselves objects of scientific inquiry. Recent progress in mechanistic interpretability (MI) has made it possible to identify neurons, features, circuits, population structures, and…
Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
Evelyn Y. Garland, Carola F. Berger
In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable,…
FERN: Cross-Benchmark Table Retrieval for Text-to-SQL with Frozen Retrievers and Learned Ranking
Arjun Rao, Nishant Gopinath
Text-to-SQL systems over large pooled catalogs must first retrieve the tables a question needs. We compare against the published table recall of RASL, which uses Claude 3.5 models to extract keywords and select tables, on pooled BIRD, Spider, and Fiben catalogs. FERN (Feature-Engineered Ranking with No generative…
BoviShift: A Six-Year Multi-Attribute Audit of Visual Cattle Phenotyping Across Animals and Time
Mobasshir Bhuiya Shagor, Nilambar Halder Tonmoy, Md Saef Ullah Miah
Computer vision offers a scalable, non-contact means of estimating livestock traits, but correlated images and video frames make reliable evaluation difficult. Image-random splitting can place views of the same animal in both training and test sets, while deployment further requires transfer to animals captured in…
C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference
Guorui Lu, Qinyu Chen
Visual Question Answering (VQA) imposes substantial computational overhead on vision-language models (VLMs), motivating model-agnostic input reduction methods that can be readily applied across diverse VLMs, including in black-box settings. Simply enforcing a visual-token cap reduces computation, but it can discard…
Bayesian inverse problems and epidemic-threshold uncertainty for a heterogeneous SIS reaction-diffusion model
Duc-Lam Duong
We study Bayesian inference of persistence from early observations of a heterogeneous susceptible--infected--susceptible (SIS) reaction--diffusion model with standard incidence. We show that the leading prevalence dynamics depend on the unknown coefficients only through the difference between the transmission and…
A Theory of Cross-Validation Variance
Nathaniel S. O'Connell, Jaime L. Speiser
Cross-validation estimates predictive performance by repeatedly splitting the data into training and validation sets, fitting the model on the first and evaluating it on the second. Every observation influences the estimate in two roles, through its own evaluation when it is held out and through the models it helps…
UGG: Unified Generative Geometry Model
Amani Kiruga, Zhiyi Li, Ruojin Cai et al.
Understanding 4D scenes is a core challenge in visual intelligence, requiring models to jointly capture scene geometry, appearance, and dynamics from partial observations. However, existing approaches are subdivided into feedforward models for direct geometric prediction, and generative models for visual synthesis.…
Metric-Aligned Group Relative Policy Optimization for Explainable Deepfake Detection
Luka Dragar, Peter Peer, Vitomir Štruc et al.
Deepfake detectors are commonly evaluated on real/fake classification alone, but real-world applications require explanations of the visual evidence behind each prediction. Joint vision-language models struggle with authenticity assessment, producing "real" narratives for manipulated images. To address this, we…
One Policy for 100 Household Tasks: Our Solution for the 2026 BEHAVIOR Challenge
Ilia Larchenko, Gleb Zarin, Atindra Nair et al.
We describe our solution for the 2026 BEHAVIOR Challenge: 100 long-horizon household tasks in the OmniGibson simulator. We placed 9th on the final leaderboard, the only independent team in the top 10. The core of the solution is a single vision-language-action (VLA) model, one checkpoint for all 100 tasks, built on…
Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications
Sourish Gunesh Dhekane, Abinaya Kumar, Torsten Woertwein et al.
Time-Series Foundation Models (TSFMs) are increasingly used in sensor applications, where sampling frequency (SF) varies across sensors, devices, and operating modes (e.g., power saving). Ideally, TSFMs must remain effective during such SF changes, provided the SF retains task-critical bandwidth. In this paper, we…
Earlybird: Predictive Streaming Speech Recognition in 29M Parameters
Sahil Mahendrakar
Streaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. For a voice agent every millisecond counts: the sooner the words are outputted, the sooner the agent can start a search or plan its reply. We present Earlybird, a 29M-parameter streaming recognizer (16.8 MB…
OnlyAct: Extracting Action Representations from Foundation Models for World Models
Runjia Li, Minghao Chen, Junyu Xie et al.
Video world models promise general-purpose interactive simulators, but their training is limited by action supervision: action labels are scarce, fragmented across incompatible specifications, and do not scale with the unlabeled video pretraining corpus. A common workaround jointly trains an action encoder to…
Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning
Souhaila Djaffal, Amna Jamal, Gagana Madhugiri Devaraja et al.
Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially…
Exploring Post-Hoc Disentanglement of Audio Foundation Models for Music Similarity
Lucas de Souza Brandão, Gabriel da Costa Merlin, Diego Furtado Silva
Audio foundation models like CLAP, MuQ, and MERT excel at capturing general musical similarity. On the other hand, their entangled latent spaces limit interpretability and fine-grained attribute control. Conditional Similarity Networks (CSN) address this by pairing a backbone representation model with learned masks…
Causal Concept Explanations for Deep Neural Models
Josh Rountree, Pulkit Verma, Oswin So et al.
Concept-based explanations in neural models are important for the development, certification, and adoption of autonomous systems. Yet, interpretability remains correlational. Without methods to guide and quantify causal relationships between explanations, a concept explanation can be provided without being…
Discovering Equations for the Thermodynamics of South Asian Monsoon Precipitation
Savannah L. Ferretti, Jane W. Baldwin, Michael S. Pritchard et al.
South Asian monsoon precipitation depends on the thermodynamic structure of the lower troposphere, but how its ingredients combine to shape precipitation remains unclear, partly because this dependence is nonlocal in the vertical. We use symbolic distillation, which combines neural networks and symbolic regression,…
REAL Loss: Optimizing Real Expected Acceptance Length for Speculative Decoding
Yu Tian
Speculative decoding accelerates LLM inference by having a draft model propose multiple tokens for the target model to verify in one pass. The speedup is governed by the expected acceptance length (EAL), yet standard training objectives such as cross-entropy, KL divergence, and total variation focus only on…
A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)
Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald et al.
Low-rank adaptation (LoRA) is the de facto method for parameter-efficient fine-tuning of large neural networks, achieving strong task adaptation with minimal trainable parameters and low optimization cost. Beyond this efficiency, practitioners have observed two striking properties: \textit{robustness to…
Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models
Amir Mann, Jonathan Fhima, Shaked Brody et al.
Diffusion Language Models (DLMs) have emerged as effective alternatives to autoregressive models for latency-critical tasks, enabling faster token generation. Recent advances employ block diffusion with self-editing capabilities, where each block refines tokens iteratively before advancing to the next one. Yet each…
An Energy-Based Perspective on Machine Learning
Bo Dai, Yilun Du
Energy-based models (EBMs) define a distribution through a scalar energy, $p_θ(x)\propto\exp(-E_θ(x))$, and are usually presented as one model family among many. This tutorial has a broader goal: beyond introducing EBMs, it uses them as a single lens that connects the different aspects of machine learning. Any EBM…
Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models
Dong Han, Jin Zhang, Kunyue Yang
Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of…
What Factors Matter for Collection-Level Counting with Human-AI Collaboration?
Seoyun Jeong, Logan Lawrence, Owen L. Martin et al.
Many scientific and policy decisions require estimating the total number of target objects across a large image collection. Exhaustive human labeling is often infeasible, while raw model predictions can be biased, especially under domain shift. Recent human-AI estimation methods combine imperfect model predictions…
Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process Critics
Marco Chan, Christos Evripidou, Liqiu Dong et al.
Start-ups and grade changes remain largely operator-driven, while developing and maintaining dynamic models for model-based control requires substantial engineering effort. Hybrid Offline Learning and Online Optimisation (HOFLON) uses one-step offline reinforcement learning to select actions from historical…
From Video Frames to Robot Meta-Frames: A Unified Latent Interface for World Action Models
Guoqiang Liang, Yiqi Lin, Yanzhe Chen et al.
Pretrained video diffusion models (VDMs) offer a powerful foundation for World Action Models (WAMs), which jointly predict robot actions and future observations. Building such models requires injecting low-dimensional robot signals (e.g. proprioception, actions, and values) into a latent space shaped by natural…
ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces
Jiahang Lin, Wanying Ren, Wanghan Xu et al.
Research agents achieve increasingly strong benchmark scores, yet these scores do not necessarily translate into reliable delivery in ongoing research projects. Many research-agent benchmarks emphasize standalone tasks and relatively self-contained workflows in clean or curated workspaces. However, researchers ask…
The Unused Input: The Initial State as a Conditioning Interface for Recurrent TSFMs
Bernhard Voggenberger, Christian Ganhör, Levente Zólyomi et al.
Time series foundation models (TSFMs) forecast unseen series without task-specific training. Increasingly they are built on recurrent backbones, whose constant per-step cost makes long-context inference cheap, and which, unlike transformers, carry a state. A recurrent backbone computes its prediction from two…
EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities
Zhengxiang Huang, Yujie Sun, Shengheng Chen et al.
Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, graph construction, operators, and hardware backends. Existing coding agents often…
CLADE: Category-Level Answering from Deficient Evidence in Retrieval-Augmented Language Models
S M Rayeed, Charles V. Stewart, Yao Ma
Retrieval-augmented systems often retrieve passages that are accurate and relevant but state the answer at a coarser level of granularity than the question requires. For example, a question may ask which specific disease a drug treats (familial hyperlipidemia), while the retrieved passage mentions the broader…
AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models
Zihan Chen, Lei Nico Zheng, Di Zhu
Users often complain that AI assistants such as ChatGPT are getting worse. Some versions do change, but human evaluation leaves a second possibility untested: the people judging may change. We separate the two on Chatbot Arena, a public platform where people compare answers from two anonymous large language models…
Forward-Value Discretization: Faster Stochastic Diffusion Sampling Without High-Order Approximation
Yuchen Jiao, Na Li, Changxiao Cai et al.
Stochastic diffusion samplers often require substantially more neural function evaluations (NFEs) than deterministic samplers to achieve comparable sample quality. Although higher-order discretization accelerates deterministic sampling, its benefits for stochastic sampling remains unclear. We establish matching…
When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
Runxuan Tang, Haoyu Gao, Yuyan Ding et al.
LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an…
Auditing the Judge: Internal Signals for LLM Reasoning Assurance
Mayank Gulati, Gerhard Wunder
Language-model systems use self-judgment to decide which answers to release, review, or recompute. Because intervention is costly, an assurance score must rank errors well at the available budget, not merely over the full ranking. We compare the judge's continuous verdict-token score with a supervised correctness…
PSL-RGHA: Parallel Split Learning with Reference Gradient Half-Space Alignment for Mitigating Gradient Divergence
Han Li, Zheng Lin, Miao Yang et al.
The escalating complexity of deep neural networks hinders the deployment of federated learning (FL) on resource-constrained devices, especially for multimedia applications such as on-device image classification and speech recognition. Parallel split learning (PSL) has emerged as a promising solution by offloading a…
Multimodal Abstention That Preserves Acquired Correct Answers
Jinyuan Zhang
Adding abstention to a task-adapted multimodal model can discard correct answers, including capabilities acquired during adaptation. We formulate abstention repair as maximizing correct abstention on unanswerable questions under a budget on newly lost correct answers. We propose ReFrain (Regression-Free…
TaoMate-R1: Temporal Role Specialization for Streaming Multi-Reference Video Generation
Qijun Gan, Chenwei Zhang, Xinyang Li et al.
Streaming multi-reference video generation establishes a scene from specified people and objects, then continues it under changing instructions. We introduce TaoMate-R1, a streaming multi-reference generator that organizes adaptation parameters through temporal role specialization. It assigns separate low-rank…
LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation
Yu Dong, Hong Li, Qiang Sun et al.
Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they…
Ninety-Six Ways to Measure a Scribe: Fragmented Evaluation of Ambient Scribes in Healthcare
Amama Mahmood, Shiye Cao, Laura Fleig et al.
Ambient artificial intelligence (AI) scribes have moved rapidly from experimental pilots to enterprise-wide deployment across health systems, promising reduced documentation burden and improved clinician experience. While research evaluating these tools has expanded quickly, there are no agreed-upon protocols or…
Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning
Wenqi Zhou, Leonardo Baldo, Kai Goebel et al.
Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this…
Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication
Ofri Elbaum, Amit Malik, Tomer Malkevich et al.
Children's peer conflicts increasingly play out in group chats, where tone and timing are stripped away, and a hurtful message is easier to send than to say aloud. We present Lilo, a multi-agent conversational system that lets children practice such conversations, so they are better prepared when they encounter…
Elastic-WAM: Adaptive Spatiotemporal Imagination for Efficient Robot Control
Haitian Li, Tianfu Li, Xuxi Zhao et al.
World-Action Models improve robot control by predicting future visual dynamics, but iterative video denoising incurs substantial inference overhead. Recent approaches reduce this cost through partial future denoising, yet typically rely on fixed refinement budgets. Our empirical observations reveal that preferred…
A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents
Jingjing Jiang
Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of…
Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization
Shuting Yang, Shuxin Li, Linyan Dai et al.
Text-to-image diffusion models can learn and reproduce an individual's identity from only a few reference photos, creating risks of unauthorized and misleading content generation. Proactive defenses address this risk by adding adversarial perturbations to facial images before release, thereby disrupting identity…
Personalized Affective Perception via Continual Learning in Human-Agent Negotiation
Mehmet Onur Keskin, Berk Buzcu, Nikhil Churamani et al.
Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that…
SinkState: On-the-Fly SVD of Recurrent States for Efficient Hybrid LLM Serving
Haolin Jiang, Weihang Li, Zhongzhu Zhou et al.
Hybrid models combine softmax attention with linear attention, which compresses history into fixed-size recurrent states to balance model quality and inference efficiency. However, linear attention has not pushed this compression to its limit: we find that the queries, keys, and values of linear layers concentrate…
An AI Assistant for Automating Anti-Corruption Expertise of Draft Legislation Based on the TRACE Framework
Serhii Zabolotnii, Alina Tarasova
We present an AI assistant for automating anti-corruption expertise of draft legislation based on the TRACE architecture, designed to screen bills for corruption risks: pinpoint provisions an expert would criticise and name the regulatory defect in each. The pipeline combines a deterministic parsing core,…
PARLEY: Evaluating LLM Collaboration Through Cooperative Asymmetric Puzzles
Javier Hernandez, Andrew D. Wilson
As large language models power autonomous agents, understanding how they collaborate and where they fail becomes critical. We introduce PARLEY, an extensible platform for studying LLM agent collaboration through four asymmetric puzzle tasks grounded in cognitive psychology (referential communication, joint…
Dyship: Leveraging Acoustic Features For Speaker Relationship Classification From Dyadic Conversations
Kieran Sturges, Thomas Thebaud, Yaohan Guan et al.
We introduce DyShip, a framework for classifying speaker familiarity and kinship from dyadic conversations in the Seamless Interaction corpus. We compare five speech representations: spectrograms, MFCCs, self-supervised WavLM representations, x-vectors, and estimated articulatory movements. Spectral features…
StaRSE: Compact Russian Sentence Embeddings with a Sign-Coded Static Encoder
Boris Malashenko, Ivan Jarsky, Egor Soldatov et al.
Transformer sentence encoders provide strong retrieval quality, but their inference cost becomes a bottleneck when embeddings must be produced on CPUs or refreshed frequently. We introduce StaRSE, a compact Russian static sentence encoder that removes Transformer inference at deployment time: token directions are…
ViGA-FLAME: Aligning Latent Visual and Geometric Representations for Robust 3D Head Expression Estimation
Wen Hao He, Jiacheng Wu, Jie Chen
Estimating 3D head expression from a single image requires mapping visual appearance to underlying facial geometry. We propose ViGA-FLAME, a two-stage framework that aligns semantic visual features with a structured geometric latent space. First, a Parametric-Geometric Variational Autoencoder (PG-VAE) learns a…