TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
hub
Audio flamingo 2: An audio- language model with long-audio understanding and expert rea- soning abilities
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 16roles
background 3polarities
background 3representative citing papers
RoleJudge is a multidimensional evaluation framework for speech-character alignment in audio LLMs, backed by the RoleChat dataset and multi-stage RL training with standard alignment to reduce reward issues.
Hybrid two-stage diffusion transformer architecture for instruction-guided audio editing via rectified flow that performs joint attention at low resolution then alternates joint and cross-attention at high resolution for improved performance and efficiency.
Introduces RAIL, a CHC-grounded benchmark with five core auditory capabilities to assess LALMs beyond task-centric metrics, showing uneven model performance.
CoAT adds a continuous latent thinking space to LALMs via expert distillation to retain acoustic information, yielding gains on audio reasoning, understanding, music, emotion, and transcription benchmarks across three models.
Audio-Interaction unifies offline and online audio tasks into one streaming model via the SoundFlow framework and a new 2.6M-item streaming corpus, enabling real-time instruction following and proactive responses.
HeadRouter prunes audio tokens more effectively by dynamically routing based on per-head importance for semantic versus acoustic tasks, exceeding baseline performance at 70% token retention on Qwen2.5-Omni models.
SpotSound adds a hallucination-suppressing objective and a needle-in-haystack benchmark to audio-language models, reaching state-of-the-art temporal grounding while keeping general task performance.
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
ALM2Vec learns unified audio embeddings from large audio-language models for text-audio retrieval, instruction-aware retrieval, and other tasks across domains.
Visual tokens enter VLMs as raw signals and are reshaped differently by in-context versus layer-injection paradigms, each capturing distinct frequency characteristics that drive task performance.
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
TinyGiantALM, a compact 1.5B audio-language model with instruction-aware refinement, achieves 46.4% zero-shot accuracy on MMAR and outperforms models up to 8x larger in mixed-modality tasks.
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.
citing papers explorer
-
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
-
Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning
RoleJudge is a multidimensional evaluation framework for speech-character alignment in audio LLMs, backed by the RoleChat dataset and multi-stage RL training with standard alignment to reduce reward issues.
-
Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow
Hybrid two-stage diffusion transformer architecture for instruction-guided audio editing via rectified flow that performs joint attention at low resolution then alternates joint and cross-attention at high resolution for improved performance and efficiency.
-
RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark
Introduces RAIL, a CHC-grounded benchmark with five core auditory capabilities to assess LALMs beyond task-centric metrics, showing uneven model performance.
-
Continuous Audio Thinking for Large Audio Language Models
CoAT adds a continuous latent thinking space to LALMs via expert distillation to retain acoustic information, yielding gains on audio reasoning, understanding, music, emotion, and transcription benchmarks across three models.
-
Audio Interaction Model
Audio-Interaction unifies offline and online audio tasks into one streaming model via the SoundFlow framework and a new 2.6M-item streaming corpus, enabling real-time instruction following and proactive responses.
-
HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models
HeadRouter prunes audio tokens more effectively by dynamically routing based on per-head importance for semantic versus acoustic tasks, exceeding baseline performance at 70% token retention on Qwen2.5-Omni models.
-
SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
SpotSound adds a hallucination-suppressing objective and a needle-in-haystack benchmark to audio-language models, reaching state-of-the-art temporal grounding while keeping general task performance.
-
Step-Audio 2 Technical Report
Step-Audio 2 integrates a latent audio encoder, reasoning-centric reinforcement learning, and discrete audio token generation into language modeling to deliver state-of-the-art performance on audio understanding and conversational benchmarks.
-
ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models
ALM2Vec learns unified audio embeddings from large audio-language models for text-audio retrieval, instruction-aware retrieval, and other tasks across domains.
-
The Hidden Evolution of Disguised Visual Context inside the VLM
Visual tokens enter VLMs as raw signals and are reshaped differently by in-context versus layer-injection paradigms, each capturing distinct frequency characteristics that drive task performance.
-
Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization
MAPO is a dual-branch RL framework using modality relevance masks from cross-modal differential entropy and auxiliary attention losses to reduce late-stage modality collapse in audio reasoning models and improve benchmark results.
-
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
A survey of Large Audio Language Models that establishes a taxonomy of trustworthiness vulnerabilities and proposes a Defense-in-Depth roadmap for audio intelligence.
-
TinyGiantALM: A Compact Audio-Language Model for Intent-Aware Reasoning under Resource Constraints
TinyGiantALM, a compact 1.5B audio-language model with instruction-aware refinement, achieves 46.4% zero-shot accuracy on MMAR and outperforms models up to 8x larger in mixed-modality tasks.
-
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
-
OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
OmniFysics is an omni-modal network using a dynamic physical data engine and evolutive tuning to improve performance on multimodal benchmarks and physics-oriented tasks.