arXiv AI
Jul 21
Environment-free Synthetic Data Generation for API-Calling Agents
arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
Hugging Face Trending Papers
Jul 21
SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.
Hugging Face Trending Papers
Jul 21
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e. g.
Hugging Face Trending Papers
Jul 21
PLAID-PRF: Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness.
Hugging Face Trending Papers
Jul 20
When Does Machine Learning Beat Value Sorting? A Three-Dataset Diagnostic of Exposure-Weighted Shipment Prioritization
Delay-risk models are usually judged by predictive accuracy. What matters in practice is narrower: with capacity to review only a few shipments, which ones should a manager check first?
Hugging Face Trending Papers
Jul 20
Patch Policy: Efficient Embodied Control via Dense Visual Representations
Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine-grained spatial detail and the benefits of large-scale visual pre-training.
Hugging Face Trending Papers
Jul 20
Causal Discovery on Irregular Time Series
Causal discovery methods have shown strong performance in temporal systems, but they typically rely on regular and discrete lag structures, limiting their applicability to regularly sampled data. However, many real-world tasks require dealing with irregularly sampled streams of events, such as sensor streams, healthcare data, and financial transactions.
Hugging Face Trending Papers
Jul 20
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents.
Hugging Face Trending Papers
Jul 20
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
Multimodal video misinformation detection is commonly formulated as a holistic video-understanding task, where the entire video and its associated content are processed and judged in a single pass. However, real-world misinformation often exhibits a sparse and compositional evidence structure: a reliable decision may depend on only a few coupled clues, while most video content contributes limited additional information.
Hugging Face Trending Papers
Jul 20
SAR Vessel Detection and Gross Tonnage Estimation from Heterogeneous Datasets for Dark Vessel Identification
Detecting vessels engaging in illegal activities is of paramount importance for maritime security. One of the major goals is to detect dark vessels, ships that disable their transponders to evade surveillance.
Hugging Face Trending Papers
Jul 20
The Shared Discovery Paradox: How a One-Answer Rule Turns Better Information into Worse Search
Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view. In a discovery problem, this can improve beliefs while reducing coverage.
Hugging Face Trending Papers
Jul 20
Adaptive Mamba Neural Operators
Accurately solving partial differential equations (PDEs) on arbitrary geometries and a variety of meshes is an important task in science and engineering applications. In this paper, we propose Adaptive Mamba Neural Operators (AMO), which integrates reproducing kernels for state-space models (SSMs) rather than the kernel integral formulation of SSMs.
Hugging Face Trending Papers
Jul 20
SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices.
Hugging Face Trending Papers
Jul 20
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters.
Hugging Face Trending Papers
Jul 20
Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding
Spatial understanding is crucial for foundation models (FMs), and maps have long helped humans organize and reason about geographic information. This study examines whether choropleth maps remain useful for machine spatial understanding when models can directly process structured geodata.
Hugging Face Trending Papers
Jul 20
A Geometric Perspective on Stabilizing Value Conflict Resolution
Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF). To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain.
Hugging Face Trending Papers
Jul 20
MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors
Classical image correspondence is solved at the level of sparse keypoints or dense pixels, but the systems that consume these matches - object-level mapping, topological navigation, scene-graph maintenance - reason about whole objects. Recent work narrows this gap by matchng directly at the level of instance segments: a class-agnostic segmenter partitions each image, and per-segment descriptors are obtained by pooling features from large 3D foundation models over the masks.
Hugging Face Trending Papers
Jul 20
Chemical filters for ultra-high-throughput materials screening and generation
Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles, which limits the reliability and interpretability of generative materials design.
Hugging Face Trending Papers
Jul 20
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores.
Hugging Face Trending Papers
Jul 20
Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA
Endoscopic visual question answering (VQA) increasingly asks complex questions that combine several endoscopic answer components rather than isolated factual queries. Such complex answers may be scored as correct even when the same model fails on associated atomic questions.