TAVIS is a released benchmark showing active vision improves imitation learning in a task-dependent manner, multi-task policies struggle with shifts, and imitation produces human-like anticipatory gaze.
hub
Communications of the ACM , volume=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
other 1
citation-polarity summary
representative citing papers
DeTox-Fed uses federated graph neural networks on local conversation graphs to detect toxic discussions in the Fediverse while keeping all raw data and labels on individual instances.
TikTok's FYP algorithm changes content based on user signals yet reverts to unwanted topics once explicit disinterest stops, with the strongest signal buried in the interface.
Participatory provenance auditing of Canada's AI strategy consultation shows official AI summaries exclude 15-17% of participants more than random baselines, with 33-88% exclusion for dissent clusters.
PaLI jointly scales a 4B-parameter vision transformer with language models on a new 10B multilingual image-text dataset to reach state-of-the-art results on vision-language tasks while keeping a simple modular design.
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
TAP couples a learner-conditioned policy with diffusion inpainting to generate and selectively inject high-utility tabular augmentations, yielding up to 15.6 pp accuracy gains and 32% RMSE reduction on seven datasets under severe scarcity.
Mage shows compile-pass rate is anti-correlated with functional correctness in LLM game scene generation; direct NL-to-C# yields 43% runtime but F1~0.12 structure, while IR conditioning recovers structure (F1 up to 1.0) but halves runtime, with granularity levels statistically equivalent.
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
citing papers explorer
-
TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning
TAVIS is a released benchmark showing active vision improves imitation learning in a task-dependent manner, multi-task policies struggle with shifts, and imitation produces human-like anticipatory gaze.
-
DeTox-Fed: Detecting Toxic Conversations in the Fediverse with Federated Graph Neural Networks
DeTox-Fed uses federated graph neural networks on local conversation graphs to detect toxic discussions in the Fediverse while keeping all raw data and labels on individual instances.
-
When 'For You' Isn't For You: Measuring User Agency in TikTok's Algorithmic Feed
TikTok's FYP algorithm changes content based on user signals yet reverts to unwanted topics once explicit disinterest stops, with the strongest signal buried in the interface.
-
Participatory provenance as representational auditing for AI-mediated public consultation
Participatory provenance auditing of Canada's AI strategy consultation shows official AI summaries exclude 15-17% of participants more than random baselines, with 33-88% exclusion for dissent clusters.
-
PaLI: A Jointly-Scaled Multilingual Language-Image Model
PaLI jointly scales a 4B-parameter vision transformer with language models on a new 10B multilingual image-text dataset to reach state-of-the-art results on vision-language tasks while keeping a simple modular design.
-
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
-
Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
TAP couples a learner-conditioned policy with diffusion inpainting to generate and selectively inject high-utility tabular augmentations, yielding up to 15.6 pp accuracy gains and 32% RMSE reduction on seven datasets under severe scarcity.
-
Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate
Mage shows compile-pass rate is anti-correlated with functional correctness in LLM game scene generation; direct NL-to-C# yields 43% runtime but F1~0.12 structure, while IR conditioning recovers structure (F1 up to 1.0) but halves runtime, with granularity levels statistically equivalent.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
Towards Expert-Level Medical Question Answering with Large Language Models
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
-
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
AGIEval shows GPT-4 exceeding average human scores on SAT Math at 95% and Chinese college entrance English at 92.5%, while revealing weaker results on complex reasoning tasks.
-
StarCoder: may the source be with you!
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.