LoCo compresses LLM reasoning chains by 41.7-45.4% on math tasks
LoCo trains models to stop overthinking using local preference learning on self-generated traces.
Stories per day · 30 days
2 RSS
Relatedpersonalization2benchmark1dpo1dueling-bandits1libero1llm-agents1llm-judges1positional-bias1rationales1reasoning-compression1reward-models1robotics1test-time1vla1
11 stories, newest first · one card per story
Stories tagged #preference-learning
DeCert supervises generative reward models on rationale quality
DeCert raises position-consistent accuracy by up to 14.8 points without reference explanations.
ID-TAP personalizes LLM agents from binary response comparisons
Within a fixed ten-round comparison budget, ID-TAP led aggregate results on seven user-conditioned generation benchmarks.
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
LIBERO-PeRM benchmarks whether robot policies satisfy user preferences separately from completing manipulation tasks.
Video Generation Models: A Survey of Post-Training and Alignment
Survey maps video-generation post-training into supervised, distillation, preference, and inference-time alignment methods.
Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling
P-TTT personalizes reward models with test-time fast weights, beating in-context preference conditioning without backprop.
Improving LLM Collaboration via Multi-Agent Preference Learning
MAPL improves multi-agent LLM collaboration by learning from preferences instead of hard-to-specify joint rewards.
Context-Continuous Preference Learning for Exoskeleton Personalization
A Gaussian-process preference model shares nearby-context feedback to personalize ankle and elbow exoskeleton assistance with less data.
CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
CARD personalizes LLMs with cluster LoRA adapters and decoding-time preference vectors, beating LaMP and LongLaMP baselines.
Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
PsPLUG keeps user personalization when explicit style instructions would otherwise collapse customized LLM behavior.
You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs
Study quantifies DPO-tuned LLMs undershooting requested emotional intensity, tracing the gap to candidate-pool extremity rather than conditioning format.