norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers2 hours ago
ResearchDaily Papers

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

The paper explores how selecting specific poisoned examples can significantly impact the success of backdoor attacks on large language models. It introduces SAILS, a method that optimizes poison set selection to increase attack effectiveness by up to 30 percentage points compared to existing methods.

Open original
SIGNAL FROM THE SOURCE
2
source votes
Tracking sinceSeptember 15, 20262 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 14, 2026Aashiq Muhamed, Mona T. Diab, Virginia Smith
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

2 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This research highlights the importance of poison set selection in backdoor attacks, showing that the right choice can drastically increase attack success rates. SAILS provides a systematic way to identify effective poison sets, which could inform better defense strategies against such attacks.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

The paper introduces Vidu S2, a system with two components: Vidu S2-Avatar for real-time interactive digital characters and Vidu S2-Editing for real-time video editing. It also explores real-time spatial video generation for both components. Compared to its predecessor, Vidu S2-Avatar offers improved real-time 720p video generation, dynamic reference updates, and enhanced instruction following. Vidu S2-Editing enables real-time video stream editing with features like style rendering and background replacement.

5 days agoDaily Papers

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

PhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.

yesterdayDaily Papers

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

ZGCM-1 is a 7B parameter foundation model designed for math and agentic search, emphasizing efficiency through architectural and system co-design, progressive curriculum learning, and an AI-native R&D workflow. It demonstrates competitive performance against larger models on mathematical and search tasks, with improvements in training efficiency and open-source availability of training materials.

4 days agoDaily Papers

Atria Dawn: The Dawn of Agentic Superintelligence

Atria Dawn Preview is a foundation agentic language model designed for scientific research and engineering workflows, trained via a Verifiable Experience Pipeline that connects tool-mediated interactions to executable environments and externally verified outcomes. It achieves competitive performance across 16 benchmarks and shows potential for human-AI collaboration in research and development.

yesterdayDaily Papers

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

ReactHuman is a benchmark for evaluating how well embodied multimodal large language models (MLLMs) can make quick, human-like decisions in response to sudden physical dangers. It includes over 1,000 reproducible scenes with precise physics-based simulations and measures reactions based on reasonableness, safety, and physical accuracy.

6 days agoDaily Papers

AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video

AlayaVista is a streaming video world model that separates panoramic world evolution from perspective observation synthesis. It uses a pretrained panorama expansion model to create a 360-degree scene prior and evolves it as a camera-conditioned panoramic latent state, then maps this to the requested perspective video latents.

2 days ago