BestHub
Sign in
Tagged articles
7 articles
Page 1 of 1
Machine Heart
Machine Heart
May 8, 2026 · Artificial Intelligence

How Laser Cuts Token Use by 97% with Probabilistic Superposition for Implicit Multimodal Reasoning

Laser introduces a latent‑superposition paradigm that replaces step‑by‑step token prediction with dynamic windowed alignment, achieving over 97% token‑consumption reduction, new SOTA performance on six visual benchmarks, and improved interpretability for multimodal large models.

ACL 2026Dynamic Window AlignmentLatent Superposition
0 likes · 13 min read
How Laser Cuts Token Use by 97% with Probabilistic Superposition for Implicit Multimodal Reasoning
Data Party THU
Data Party THU
May 4, 2026 · Artificial Intelligence

Why Sending a Tilde to an LLM Can Erase Your Entire Home Directory

A recent ACL 2026 paper uncovers a “Emoticon Semantic Confusion” vulnerability in large language models, where the tilde symbol (~) intended as a friendly emoticon is interpreted as the shell shortcut for the home directory, causing silent, irreversible deletions across major LLMs with a 38.6 % confusion rate.

ACL 2026LLM safetyLarge Language Models
0 likes · 9 min read
Why Sending a Tilde to an LLM Can Erase Your Entire Home Directory
Machine Heart
Machine Heart
May 4, 2026 · Artificial Intelligence

Thought-Based Gloss-Free Sign Language Translation Model for the Deaf (ACL 2026)

The paper introduces SignThought, a gloss‑free sign language translation framework that uses a latent chain‑of‑thought reasoning layer and a plan‑then‑ground decoder, evaluates it on five benchmarks with state‑of‑the‑art BLEU‑4 and ROUGE scores, and releases a large new Hong Kong sign language dataset.

ACL 2026BenchmarkGloss-Free
0 likes · 11 min read
Thought-Based Gloss-Free Sign Language Translation Model for the Deaf (ACL 2026)
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
May 2, 2026 · Artificial Intelligence

RouteMoA: Dynamic Routing Without Pre‑Inference for Efficient Multi‑Agent Mixtures

RouteMoA moves model selection ahead of inference by using a lightweight scorer to predict each model's suitability from the query, dramatically cutting computation cost and latency while preserving or improving accuracy, as demonstrated on a 15‑model pool with up to 90% cost reduction and 64% latency reduction.

ACL 2026Dynamic RoutingInference Optimization
0 likes · 9 min read
RouteMoA: Dynamic Routing Without Pre‑Inference for Efficient Multi‑Agent Mixtures
Machine Heart
Machine Heart
May 1, 2026 · Artificial Intelligence

LLMs Write and Evolve Code to Redefine Quantitative Factor Mining – The CogAlpha ACL Paper

The CogAlpha framework upgrades Alpha discovery from static formulas to executable Python code, organizes a 7‑layer, 21‑agent research hierarchy, iteratively evolves factor candidates, and on CSI300 10‑day prediction outperforms 21 baselines with a 16.39% annual excess return and an IR of 1.8999, demonstrating that large models can actively participate in the discovery process.

ACL 2026Alpha MiningEvolutionary Algorithms
0 likes · 9 min read
LLMs Write and Evolve Code to Redefine Quantitative Factor Mining – The CogAlpha ACL Paper
Machine Heart
Machine Heart
Apr 28, 2026 · Artificial Intelligence

Can LLMs Answer More Accurately While Writing Less? Introducing SHAPE’s Reasoning Tax

The SHAPE framework (Stage‑aware Hierarchical Advantage via Potential Estimation) adds a milestone‑based “reasoning tax” to large language model inference, providing step‑wise correctness signals and penalizing verbosity, which yields an average 3% accuracy gain and a 30% reduction in token consumption across multiple math‑reasoning benchmarks.

ACL 2026LLMMathematical Reasoning
0 likes · 10 min read
Can LLMs Answer More Accurately While Writing Less? Introducing SHAPE’s Reasoning Tax
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Apr 23, 2026 · Artificial Intelligence

ControlAudio: Script‑Driven, Time‑Precise Text‑to‑Audio Generation Presented at ACL 2026

ControlAudio, a progressive diffusion framework introduced by Tsinghua researchers, unifies text, timing, and phoneme modeling to enable precise control over when sounds occur and what is spoken, achieving superior alignment and intelligibility while preserving high‑fidelity audio generation.

ACL 2026ControlAudioText-to-Audio
0 likes · 11 min read
ControlAudio: Script‑Driven, Time‑Precise Text‑to‑Audio Generation Presented at ACL 2026