MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiBench benchmark.
Title resolution pending
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 15representative citing papers
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
LLMs display inconsistent factual recall across different surface forms of the same entity, with greater robustness to minor spelling changes than to aliases or abbreviations.
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
SWE-Mutation benchmark shows current LLMs achieve low verification (10.20%) and detection (36.15%) rates on 2,636 mutated variants, exposing weaknesses in generating reliable test suites.
Cross-entropy method sampling reduces inferences needed to estimate five-nines LLM reliability by up to 156x on parameterized GSM8K templates, revealing reliability differences hidden by saturated accuracy scores.
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
Republican posts are more toxic than Democratic ones, but Democratic content draws more toxic replies due to higher volume of Republican cross-partisan engagement.
The authors introduce a validation framework showing LLMs can pull causal links from disaster social media but require checks against post-event evidence to avoid relying on model priors.
Multilingual pooling for quality classifiers outperforms monolingual baselines in rank stability and accuracy for LLM pretraining data selection across high- and low-resource languages.
citing papers explorer
-
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiBench benchmark.
-
Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain
LLMs copy biased analyst ratings in investment decisions but a new detection method encourages independent reasoning and can improve stock return predictions beyond human levels.
-
Logic-Regularized Verifier Elicits Reasoning from LLMs
LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
-
Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms
LLMs display inconsistent factual recall across different surface forms of the same entity, with greater robustness to minor spelling changes than to aliases or abbreviations.
-
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?
SWE-Mutation benchmark shows current LLMs achieve low verification (10.20%) and detection (36.15%) rates on 2,636 mutated variants, exposing weaknesses in generating reliable test suites.
-
Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks
Cross-entropy method sampling reduces inferences needed to estimate five-nines LLM reliability by up to 156x on parameterized GSM8K templates, revealing reliability differences hidden by saturated accuracy scores.
-
Weighted Rules under the Stable Model Semantics
Weighted rules extend stable model semantics to support probabilistic reasoning, model ranking, and statistical inference in answer set programs.
-
Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
-
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
-
LIMO: Less is More for Reasoning
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
-
"F*** You Biden": Cross-Partisan Electoral Toxicity on X
Republican posts are more toxic than Democratic ones, but Democratic content draws more toxic replies due to higher volume of Republican cross-partisan engagement.
-
Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
The authors introduce a validation framework showing LLMs can pull causal links from disaster social media but require checks against post-event evidence to avoid relying on model priors.
-
Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection
Multilingual pooling for quality classifiers outperforms monolingual baselines in rank stability and accuracy for LLM pretraining data selection across high- and low-resource languages.