EditAgent expands tools and verification for agentic image editing
Experts preferred parallel listwise judging over sequential refinement in 78.5% of decided comparisons.
Stories per day · 30 days
Relatedagents1benchmarks1data-labeling1foundation-models1image-editing1llm-judges1open-source1positional-bias1preference-learning1rationales1robotics1vision-language-models1
8 stories, newest first · one card per story
Stories tagged #reward-models
Flora open robotics data engine reports SOTA caption and reward scores
Authors say Flora labels 200,000 hours a day and is about 125 times cheaper than GPT-6 Astra.
DeCert supervises generative reward models on rationale quality
DeCert raises position-consistent accuracy by up to 14.8 points without reference explanations.
Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models
Million-parameter ranking models personalize LLM generation more accurately and cheaply than billion-parameter reward models.
PoEM: Predicting RL Outcomes from Existing Policies
PoEM approximates a reinforcement-learning policy for a new reward from existing post-trained models, without extra RL.
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
A decision-only JEV judge nearly matches a top LLM judge at a fraction of the cost.
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Researchers introduce Generative Verification (GenV), a generative reward model achieving 0.961 AUROC in detecting unfaithful autoformalization that preserves solver verdicts.
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
New ROBORMBENCH benchmark shows vision-language reward models can flip robot success/failure judgments when goal instructions are paraphrased.