Benchmarks and evaluation

Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.

18,285 stories · RSS feed

Hugging Face Trending Papers
Jul 2

Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafters

Speculative decoding accelerates autoregressive generation by drafting a block of tokens that the target model verifies left-to-right, committing only the longest accepted prefix. Block (DLM-style) drafters predict the whole block in parallel, which is fast but trained with a full-block cross-entropy that supervises every position against the gold continuation -- even though inference discards every token after the first rejection.

Hugging Face Trending Papers
Jul 2

Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction

Large 3D foundation models such as MASt3R achieve state-of-the-art stereo reconstruction but are computationally demanding for deployment under strict hardware constraints -- a critical limitation in domains such as planetary exploration, where onboard computing is severely restricted. We study how far such models can be compressed through knowledge distillation, using lunar stereo reconstruction as a challenging and practically relevant case study.

Hugging Face Trending Papers
Jul 2

Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling

Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator.

Hugging Face Trending Papers
Jul 2

PARTREP: Learning What to Repeat for Decoder-only LLMs

While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is prompt repetition -- just appending a second copy of prompt before generation can redistribute grounding across positions and improve reasoning performance.

Hugging Face Trending Papers
Jul 2

SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation

LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output. Dynamic 4D scenes from text alone, in which liquids flow, particles emit, rigid bodies cascade, and articulated mechanisms move, remain largely unexplored despite their value as editable content and as physics-grounded training data for video generation and embodied AI.

Hugging Face Trending Papers
Jul 2

DL-VINS-Factory: A Modular Framework for Learned Visual Front-Ends in Visual-Inertial SLAM

Deep-learning features excel in visual matching, yet their practical value in tightly coupled visual-inertial SLAM (VI-SLAM) remains insufficiently characterized. We present DL-VINS-Factory, a unified framework that integrates learned feature extractors (ALIKED, RaCo, SuperPoint, XFeat) with either Lucas--Kanade (LK) optical-flow tracking or LightGlue (LG) descriptor matching.

Hugging Face Trending Papers
Jul 2

Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation

On-policy exploration is a crucial component for training robust Vision-Language Navigation agents, as it exposes the policy to a broader state distribution. However, such exploration inevitably leads to trajectories that deviate from expert demonstrations, resulting in a semantic mismatch between the executed visual stream and the original language instruction.

Hugging Face Trending Papers
Jul 2

InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation

Text-conditioned human interaction generation must capture both long-range temporal causality within each individual and tightly coupled coordination between partners. Existing interaction diffusion models typically denoise full sequences using bidirectional attention, which obscures causality and hinders streaming and long-horizon generation.

Hugging Face Trending Papers
Jul 2

Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing

Visual regression testing (VRT) is a standard quality assurance step in modern software release pipelines. On every change, it re-renders user interface (UI) screenshots, compares each one against an approved baseline image, and routes any detected difference to a human reviewer who decides whether it is an intended update or an unintended regression.

Hugging Face Trending Papers
Jul 2

Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging. Existing expert-pruning methods typically rely on a single aggregated importance score, which can bias the retained set toward experts favored by dominant calibration patterns.

Hugging Face Trending Papers
Jul 2

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior MLP conference study to Random Forest and XGBoost across four tabular security datasets (phishing URLs, UNSW-NB15, NF-ToN-IoT, HIKARI-2021), evaluating five attacks including three black-box methods applicable to non-differentiable tree models.

arXiv Machine Learning
Jul 2

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

arXiv:2607. 01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques.

By Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere, Nikita Menon, Stefan Heimersheim
arXiv AI
Jul 2

LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter

arXiv:2607. 00687v1 Announce Type: cross Abstract: Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the backbone itself.

By Tobias Christian Nauen, Anosh Billimoria, Federico Raue, Stanislav Frolov, Brian B. Moser, Andreas Dengel