Claims Browser

There is a striking performance gap between even the best VLMs and humans on visual text error correction tasks

"Our experiments reveal a striking performance gap between even the best VLMs and human"

Most VLMs struggle to accurately perceive visual text, resulting in frequent correction errors

"most models struggle to accurately perceive the visual text, resulting in frequent correction errors"

Action chunks are especially important for crowd navigation in bounded environments where boundary violations are treated as collisions

"ablations demonstrate that action chunks are especially important for the modified bounded benchmark"

Document-to-document LLM translation in a single pass frequently suffers from structural misalignment including sentence omissions or hallucinations

"document-to-document generation in a single pass frequently suffers from structural misalignment, manifesting as sentence omissions or hallucinations that violate the core requirement of source-target correspondence"

StarPO framework significantly enhances translation quality and structural integrity in document-level machine translation

"Experimental results across news and literary domains demonstrate that StarPO significantly enhances translation quality and structural integrity"

Compact models using StarPO can surpass GPT-4o performance while maintaining superior token efficiency

"StarPO allows compact models to surpass the performance of massive proprietary systems like GPT-4o while maintaining superior token efficiency"

Autoregressive large language models routinely generate factually incorrect outputs with high decoding confidence, limiting their deployment in high-stakes workflows

"Autoregressive large language models (LLMs) routinely generate factually incorrect outputs with high decoding confidence, limiting their deployment in high-stakes workflows."

Internal hidden-state transition dynamics during generation can signal factual errors without auxiliary decoding calls

"internal hidden-state transition dynamics during generation can signal factual errors without auxiliary decoding calls"

PoP operates within the base forward pass, adding less than 1.2% runtime latency and requiring zero additional generation passes

"The mechanism operates within the base forward pass, adding less than 1.2% runtime latency and requiring zero additional generation passes."

LLM agents commit to directional calls on unpredictable questions 54.0% of the time when shown professional-looking market panels, compared to only 6.5% when asked bare questions, across 12 frontier models

"An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked the bare question: across 12 frontier models, commitment rises from 6.5% to 54.0% as evidence is escalated."

LLMs commit to unpredictable questions just as readily when all data is fabricated, with commitment rising from 24.5% to 36.8% with fake data versus 37.6% with genuine data

"It commits just as readily when every number on the panel is invented: fabricating the entire display, so nothing the model can see is true except the question itself, still lifts commitment from 24.5% to 36.8%, statistically indistinguishable from the 37.6% produced by genuine market data."

LLMs can answer matched answerable questions with near-perfect accuracy when attached to the same panels, showing the failure is not due to incapacity

"Incapacity is not the answer: on matched answerable questions attached to the same panels, the same models answer essentially always, at near-perfect accuracy."

LLMs correctly classify questions as unknowable 90% of the time but then still commit on just 0.4% of those cases, showing the act/don't-act gate is what fails

"asked to classify a question's knowability before acting, models call it irreducible 90% of the time and then commit on just 0.4% of those. The act/don't-act gate is what fails"

The act/don't-act gate failure can be fixed through training: supervised fine-tuning of a 3B model on 540 synthetic cases drives commitment on unpredictable questions to 0.0% and transfers to three unseen domains

"Because the gate is separable, it can be trained. Supervised fine-tuning of a 3B model on 540 synthetic cases, predominantly dice, coins, jars and timers, drives commitment to 0.0% on the original cases and transfers to three unseen domains."

The trained act/don't-act gate is context-fragile and only holds when response format allows reasoning; rigid formats leave models confident and wrong on questions they otherwise answer correctly

"It does not survive everything: the gate holds exactly when the response format leaves room to reason, and rigid formats that remove that room leave the model confident and wrong on questions it otherwise answers correctly."

Video foundation models are beginning to change film and video production

"Recently, video foundation models are beginning to change film and video production"

Magpie enables applying generative models to real-time game rendering while preserving gameplay designability and reproducibility

"Magpie provides a system-level implementation path for applying generative models to real-time game rendering. It preserves gameplay designability and reproducibility, and reduces the dependence of early game prototypes on complete visual assets."

Generative models can reduce the dependence of early game prototypes on complete visual assets

"reduces the dependence of early game prototypes on complete visual assets"