Small well-performing LVLMs gain the largest benefits from test-time scaling (up to ~30% improvement), often matching or exceeding larger models, while visual tokens contribute mainly early in the reasoning chain.
Prompt repetition improves non-reasoning llms
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 11roles
background 1polarities
background 1representative citing papers
M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and symbolic recall.
PartRep selects high-NLL tokens via a lightweight early-exit gate for partial prompt repetition, retaining most full-repetition gains at 59.4% KV cache and 79% prefill FLOPs on eight benchmarks.
mmPISA-bench evaluates two LLMs on 25 reasoning questions across 43 languages and finds effective multilingual reasoning at human levels with machine translations performing equivalently to human ones.
MLP activations measured as massive activations or first four moments correlate weakly (max |Spearman| = 0.33) with in-context example quality across Llama-3.2-3B, Qwen2.5-3B, and multiple classification/generative tasks, so activation-based active learning should not be used for ICL.
PsychoPass shows adversarial LLM conversations exhibit an early geometric fingerprint in representation space that persists after removing length confounds and is detectable from short prefixes.
Prompts with higher semantic density per token improve LLM accuracy by an average of 8.4 percentage points across five models and seven benchmarks, with no added tokens or latency.
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
Optimized prompts for vision foundation models improve cowpea detection accuracy by over 0.35 mAP on synthetic data and transfer effectively to real fields without manual annotations.
citing papers explorer
-
On Test-Time Scaling for Vision-Language Models
Small well-performing LVLMs gain the largest benefits from test-time scaling (up to ~30% improvement), often matching or exceeding larger models, while visual tokens contribute mainly early in the reasoning chain.
-
M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and symbolic recall.
-
PARTREP: Learning What to Repeat for Decoder-only LLMs
PartRep selects high-NLL tokens via a lightweight early-exit gate for partial prompt repetition, retaining most full-repetition gains at 59.4% KV cache and 79% prefill FLOPs on eight benchmarks.
-
mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?
mmPISA-bench evaluates two LLMs on 25 reasoning questions across 43 languages and finds effective multilingual reasoning at human levels with machine translations performing equivalently to human ones.
-
Activation-Based Active Learning for In-Context Learning: Challenges and Insights
MLP activations measured as massive activations or first four moments correlate weakly (max |Spearman| = 0.33) with in-context example quality across Llama-3.2-3B, Qwen2.5-3B, and multiple classification/generative tasks, so activation-based active learning should not be used for ICL.
-
PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations
PsychoPass shows adversarial LLM conversations exhibit an early geometric fingerprint in representation space that persists after removing length confounds and is detectable from short prefixes.
-
Semantic Density Effect (SDE): Maximizing Information Per Token Improves LLM Accuracy
Prompts with higher semantic density per token improve LLM accuracy by an average of 8.4 percentage points across five models and seven benchmarks, with no added tokens or latency.
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
-
Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection
Optimized prompts for vision foundation models improve cowpea detection accuracy by over 0.35 mAP on synthetic data and transfer effectively to real fields without manual annotations.
- Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report Generation
- Beyond Questions: Evaluating LLM's Knowledge Expression