HuggingFace
K-EXAONE 2.0 Technical Report
This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
Learning generalizable robot manipulation policies requires large-scale and diverse demonstration data. Egocentric hu...
HuggingFace
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross...
HuggingFace
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore cri...
HuggingFace
AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities
While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visua...
HuggingFace
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks m...
HuggingFace
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
GUI agents must remember both useful experience from earlier tasks and unfinished progress in the current interaction...
HuggingFace
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate e...
HuggingFace
Self-Evolving Coding Agents
Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect r...
HuggingFace
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matchin...
HuggingFace
Multi-Task Multi-Frame Visual Piano Transcription
Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist...
HuggingFace
When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings
We identify a previously overlooked failure mode of ALiBi positional encoding: its linear bias scaling underflows flo...