Research Papers
Hugging Face Unveils SWE-Bench ProMax: A Harder, Multilingual Benchmark for AI Coding Agents
Hugging Face researchers introduce SWE-Bench ProMax, a multilingual code refactoring benchmark with 170 expert-curated instances a...
DuplexGen: Calibrating AI Turn-Taking to Human Preferences
New framework DuplexGen generates dialogues with scenario-adaptive turn-taking by calibrating LLM predictions against human prefer...
New 'Skaling' Law Couples Model Size and Data to Sharpen AI Loss Predictions
Researchers introduce the Skaling law, a generalized scaling law that couples model capacity and data via an interaction exponent,...
Multi-Agent Framework and 100K Benchmark Boost Deepfake Video Detection
Researchers introduce FaceVid-Forensics-100K, a large-scale deepfake video benchmark with fine-grained annotations, and ARGUS, a m...
Hugging Face Unveils DME: A Two-Stage Multimodal Embedding Model for Billion-Scale Search
Douyin's DME combines contrastive pre-training with training-only reasoning and reconstruction to achieve state-of-the-art results...
Hugging Face Study: Offline Top-K Distillation Cuts Memory, Boosts Throughput
A new paper from Hugging Face shows that caching teacher logits and using a chunked KL loss can make knowledge distillation for sm...
Small Cognitive Models Match Giants In-Distribution but Scale Better Out-of-Distribution
New research shows that small language models fine-tuned on human behavioral data can match a 70B baseline in-distribution, but la...
Referential Dangling: A Hidden Failure Mode in Hard Prompt Compression
New research from Hugging Face reveals that hard prompt compression methods often delete the context needed to interpret retained...
Fine-Tuned Activation Oracles Develop Concept-Specific Blind Spots, Study Finds
New research from Hugging Face reveals that fine-tuning activation oracles on a subject model that hides a concept makes them sele...
DCAS: Decoupling Scaffold Planning to Make CLI Agents Generalize
A new interception layer, DCAS, decouples planning from scaffold-specific training, enabling fine-tuned CLI coding agents to gener...
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Researchers from Harvard, MIT, and major AI labs introduce MatrAIx, a population-scale evaluation infrastructure with 8.3 billion...
SFT Conflicts, RL Coexists: New Study Explains Multi-Task Learning in LLMs
A new paper from Hugging Face reveals that supervised fine-tuning (SFT) suffers from task conflicts in multi-task training, while...