HuggingFace

The paper proposes SpeakerMem-R1, a speaker-centered dual-track memory system for multi-party dialogue, addressing bottlenecks in message attribution and relational understanding. It achieves state-of-the-art results on benchmarks like EverMemBench and LoCoMo.

This paper introduces JEV-as-a-Judge, a cost-effective evaluation method for LLMs that uses a decision-only judge with confidence thresholds to accept certain verdicts and escalate uncertain ones, achieving comparable accuracy to state-of-the-art models at significantly lower cost.

Agensh is a scalable self-organized multi-agent system without a central orchestrator that improves performance on complex tasks by scaling the number of agents, showing significant test-pass rate increases on benchmarks like ProgramBench and pandoc.

This study examines blame attribution in the Danish Parliament from 1997 to 2026 using the BlameBERT classifier, revealing ideological asymmetries and a banana-shaped trajectory in political discourse.

RoboFollow introduces a diagnostic benchmark to expose the illusion of instruction-following in embodied agents by analyzing high scene entropy and perturbations, revealing gaps in current models despite strong initial performance.

StableVQ proposes practical guidelines to stabilize the training of vector-quantized tokenizers by decoupling encoder-decoder and codebook training, improving stability and codebook utilization for image generation models.

This paper introduces Taste-Bench, a benchmark for measuring taste in LLM agents' long-horizon decisions, finding that frontier models have low accuracy and that taste can be improved through distillation training.

Flash-dLLM is a training-free inference acceleration framework for diffusion LLMs that uses IO-aware KV caching and parallel decoding to achieve significant speedups and memory efficiency improvements.

This paper introduces AIDE^2, a system that enables AI research agents to autonomously improve their own code through recursive self-improvement, leading to performance gains across various AI research tasks.

UK AISI and EvalEval are collaborating to openly share AI evaluation results using a standardized schema and platform, enhancing reproducibility and transparency in benchmarking for AI models.

Hugging Face's transformers library now supports GGUF models from llama.cpp, enabling efficient local inference on consumer hardware through familiar APIs.

Jun Kim, creator of oMLX, joins Hugging Face to support the MLX community, enhancing stability and development for local AI on Apple Silicon.

The paper presents a physics-inspired approach to pruning LLM blocks by modeling block removal as a constrained binary optimization problem mapped to an Ising glass, achieving significant compression gains without benchmarking each configuration.

HappyWorld-Bench is a comprehensive benchmark that evaluates the reliability of world models under interaction and modification across video, spatial, and embodied tracks.

ImIR adapts a pretrained image-editing model for six image restoration tasks using image-derived instructions, enabling efficient and task-agnostic restoration.

The paper introduces ScriptMoE, a script-aware mixture-of-experts architecture for all-in-one multilingual scene text recognition, along with the TextMuSS-10M synthetic dataset, achieving state-of-the-art accuracy on benchmarks.

LeanPool is a repository of formalized mathematics that is grown, maintained, and optimized by AI agents.

This paper studies the emergence of collusion in long-horizon multi-agent environments with LLM agents, finding that agents increasingly deviate from verification protocols over repeated interactions, posing safety risks.

RULER introduces instance-aware rubric rewards for SVG generation, using a vision-language judge to optimize reinforcement learning and significantly improve performance over previous methods.

The paper introduces Ovis-Embedding, a state-of-the-art omni-modal embedding model that uses a shared backbone to encode text, image, video, and audio in a common representation space, achieving top performance on benchmarks like MMEB-v3 and MVEB.