HuggingFace
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness
Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of cap...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a ph...
HuggingFace
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attenti...
HuggingFace
InSight-doc: Agentic Visual Perception for Long-Document Understanding
Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone...
HuggingFace
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs pres...
HuggingFace
The Loss Does Not See the Basis, but Adam Does
Gradient descent on a factored model W = UV^top is implicitly biased toward low-rank solutions, while Adam, starting ...
HuggingFace
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, b...
HuggingFace
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context...
HuggingFace
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be un...
HuggingFace
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization
In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates ...
HuggingFace
Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure
Benchmarks for systems that are optimized against the evaluation signal measure something different from what they cl...
HuggingFace
Omega-S: A Functional Resilience Index for LLM Fine-Tuning
Fine-tuning a large language model on new data degrades what it previously learned. We present Omega-S, a drop-in pen...