-
GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigation
score 4
关键词(4): agentic, reasoning, vision-language, embodied;顶会接收: EMNLP
-
Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models
score 4
关键词(3): vision-language, open-source, guardrails;顶会接收: ECCV
-
On the Resilience of Text-to-Video Diffusion Models to Hardware Faults
score 4
关键词(1): text-to-video;顶会接收: ICML
-
PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization
score 4
关键词(2): real-time, leaderboard;顶会接收: EMNLP
-
ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search
score 4
机构: Baidu;关键词(1): fine-tuning
-
ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization
score 4
关键词(3): lightweight, distillation, reasoning;顶会接收: EMNLP
-
A Target-Centric Survey of Quantization-Aware Training
score 4
关键词(2): quantization, deployment;顶会接收: EMNLP
-
You Know What I Mean: A Benchmark for Agentic Conversational Reference Grounding
score 4
关键词(2): agentic, tool use;顶会接收: EMNLP
-
SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs
score 4
关键词(3): latency, agentic, reasoning;顶会接收: EMNLP
-
ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
score 8
入选 HF Daily Papers;HF 热度: 4 upvotes (+1);关键词(1): text-to-image;顶会接收: EMNLP
-
Discrete Diffusion Bridges for Spatiotemporally Aligned Image Translation and Generation
score 4
关键词(1): text-to-image;顶会接收: ECCV
-
TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models
score 4
关键词(4): serving, fine-tuning, GRPO, post-training;顶会接收: EMNLP
-
How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
score 4
关键词(1): post-training;顶会接收: EMNLP
-
SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training
score 3
顶会接收: EMNLP
-
PhysWave: Physics-Guided Latent Diffusion Models for Controllable Spatial Audio Generation
score 3
顶会接收: EMNLP