Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens
Paper • 2611.07298 • Published • 6
Uracle-KULLM
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
yjoonjang
authored a
paper 1 day ago
hongst
authored a
paper 2 days ago
hongst
submitted a
paper to Daily Papers 2 days ago
yjoonjang
authored 3
papers 5 days ago
MixLID: Token-Level Language Identification in Mixed-Language Text
Paper • 2610.16601 • Published • 5
RenderRank: Learning to Rerank Text with Compressed Visual Tokens
Paper • 2609.35069 • Published • 7
KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval
Paper • 2608.01389 • Published
hongst
authored 2
papers 25 days ago
hongst
submitted a
paper to Daily Papers 25 days ago
jungseob
authored 11
papers about 1 month ago
Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
Paper • 2608.23149 • Published • 8
RenderRank: Learning to Rerank Text with Compressed Visual Tokens
Paper • 2609.35069 • Published • 7
Distilling Directional Verification
Paper • 2610.00997 • Published • 1
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
Paper • 2606.23181 • Published • 2
Recovering Off-Policy Supervision for Speculative Decoding
Paper • 2609.38795 • Published
CAST: Cost-Aware Speculative Trees from One-Pass Block Drafters
Paper • 2610.00321 • Published
Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks
Paper • 2609.37493 • Published
Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning
Paper • 2610.00320 • Published
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Paper • 2609.00355 • Published
Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding
Paper • 2609.33889 • Published
The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice
Paper • 2608.28930 • Published