WNM decouples video generation into agent-built editable 4D physical narratives that condition frozen foundation models, reducing gacha-style resampling and improving layout, motion, and camera control.
LoRA: Low-rank adaptation of large language models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
A tokenizer-free pixel embedding, position encoding, and 256-way head let frozen LLMs act as portable entropy models for lossless RGB compression across model families.
BadStyle creates stealthy backdoors in LLMs by poisoning samples with imperceptible style triggers and using an auxiliary loss to stabilize payload injection, achieving high attack success rates across multiple models while evading defenses.
TTS data augmentation and LLM error correction together cut relative WER by 40-50% on ASR models for oral cancer speech.
WILD-SAM is a fine-tuned SAM variant using phase-aware MoE adapters and wavelet subband enhancement that achieves state-of-the-art landslide detection on wrapped InSAR data.
LLM fine-tuning, RAG, and hybrid methods can build a useful knowledge base from support tickets that serves as a good starting point for root cause analysis in networks.
CoLLM unifies FL PEFT and inference on shared edge replicas via intra-replica model sharing and two-timescale inter-replica coordination, achieving up to 3x higher goodput than prior LLM systems.
citing papers explorer
-
World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration
WNM decouples video generation into agent-built editable 4D physical narratives that condition frozen foundation models, reducing gacha-style resampling and improving layout, motion, and camera control.
-
LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression
A tokenizer-free pixel embedding, position encoding, and 256-way head let frozen LLMs act as portable entropy models for lossless RGB compression across model families.
-
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
BadStyle creates stealthy backdoors in LLMs by poisoning samples with imperceptible style triggers and using an auxiliary loss to stabilize payload injection, achieving high attack success rates across multiple models while evading defenses.
-
Improving Automatic Speech Recognition for Speakers Treated for Oral Cancer using Data Augmentation and LLM Error Correction
TTS data augmentation and LLM error correction together cut relative WER by 40-50% on ASR models for oral cancer speech.
-
WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms
WILD-SAM is a fine-tuned SAM variant using phase-aware MoE adapters and wavelet subband enhancement that achieves state-of-the-art landslide detection on wrapped InSAR data.
-
LLM-Augmented Knowledge Base Construction For Root Cause Analysis
LLM fine-tuning, RAG, and hybrid methods can build a useful knowledge base from support tickets that serves as a good starting point for root cause analysis in networks.
-
CoLLM: Continuous Adaptation for SLO-Aware LLM Serving on Shared GPU Clusters
CoLLM unifies FL PEFT and inference on shared edge replicas via intra-replica model sharing and two-timescale inter-replica coordination, achieving up to 3x higher goodput than prior LLM systems.