Paper Citation Record · LEDGER

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

As of 16 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 4 inbound Pith citation observations for arXiv:2509.06461.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2509.06461 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:19:43.691285Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T08:23:29.666893Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-10T23:55:52.903831Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy3
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2a5b67c-64f8-4def-9291-00163c139acd · outbound

This paper cites Star Attention: Efficient LLM Inference over Long Sequences.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Star Attention: Efficient LLM Inference over Long Sequences

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.546665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cac38d7-b8da-48eb-a52e-f7f3d7bafba0 · outbound

This paper cites Dp-iqa: Utilizing diffusion prior for blind image quality assessment in the wild.arXiv preprint arXiv:2405.19996,.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Dp-iqa: Utilizing diffusion prior for blind image quality assessment in the wild.arXiv preprint arXiv:2405.19996,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.576633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14dc7873-6181-4b8f-bdf6-adac22422ce5 · outbound

This paper cites Vistawise: Build- ing cost-effective agent with cross-modal knowledge graph for minecraft.arXiv preprint arXiv:2508.18722,.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Vistawise: Build- ing cost-effective agent with cross-modal knowledge graph for minecraft.arXiv preprint arXiv:2508.18722,

Reference 7

Resolution: verified exact; raw_fallback, observed 2026-08-15T16:19:44.188584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 646f8f1b-9e21-45f4-b514-4813b9ae1d7d · outbound

This paper cites Mrfd: Multi-region fusion decoding with self-consistency for mitigating hallucinations in lvlms, 2025a.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Mrfd: Multi-region fusion decoding with self-consistency for mitigating hallucinations in lvlms, 2025a

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.589372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187f8fbc-ac5b-4954-9e73-4c1c971c5b0c · outbound

This paper cites DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.604994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130a646e-6e67-4bc7-a161-6c610a1a8fea · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:44.445640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4a47b18b-0307-4338-85c3-34e184585a06 · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Evaluating Object Hallucination in Large Vision-Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.616653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aacfdf11-dec1-4b6b-9b27-c0d10752de47 · outbound

This paper cites Structured Attention Matters to Multimodal LLMs in Document Understanding.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Structured Attention Matters to Multimodal LLMs in Document Understanding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.621986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f598cc-4646-4262-ba5c-cb7eec314d56 · outbound

This paper cites Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.627310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f98f819-6a45-47af-a677-3df58c7dc331 · outbound

This paper cites SLANG: New Concept Comprehension of Large Language Models.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning SLANG: New Concept Comprehension of Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.632137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 124d6a33-14e5-470f-bffd-895ff40ab780 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.637935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b367f3-9f44-48ee-b5ea-cbcc583a7662 · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.649105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61082bcc-5e41-4261-b7f1-0ced4349f1d5 · outbound

This paper cites V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.654520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a3692e-d7aa-40c3-95ec-cbad89f9a31a · outbound

This paper cites Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.660111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15710224-9697-4d87-abdd-dde34cb5df7c · outbound

This paper cites Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.665830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b0f0b57-98ec-409d-908f-de89a1a19015 · outbound

This paper cites MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.672057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35db9617-d28d-4013-84a5-d329bcca5bd0 · outbound

This paper cites TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.679677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1131f406-f9cc-4d71-8de2-db2359a9c6ee · outbound

This paper cites Factual Dialogue Summarization via Learning from Large Language Models.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Factual Dialogue Summarization via Learning from Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.685611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5407da0c-93f8-4459-8bde-453a7b9205a0 · outbound

This paper cites Write a general description of the image.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Write a general description of the image

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:44.406142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a71acdbd-f22b-4bde-a763-d0a731939cb2 · outbound

This paper cites PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression

Reference 1986

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.565364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd73f359-b963-4e7b-9e00-7cb609001b6d · outbound

This paper cites A-okvqa: A benchmark for visual question answering using world knowledge.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning A-okvqa: A benchmark for visual question answering using world knowledge

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:19:44.428222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 81252269-68f7-455b-acf3-fd21917f19c9 · outbound

This paper cites Context-DPO: Aligning Language Models for Context-Faithfulness.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Context-DPO: Aligning Language Models for Context-Faithfulness

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.553312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef3bc0a-87fe-44a9-9505-dca87e350ed1 · outbound

This paper cites Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.595045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88f0c62-f252-43fa-b6c5-9ca316a74632 · outbound

This paper cites RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T16:19:43.559195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b865cef-0eee-4883-9fe5-13a6aeb0a3a0 · outbound

This paper cites Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject.

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject

Reference 2025

Resolution: malformed identifier; no resolver link, observed 2026-08-15T16:19:43.570711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5fda0e9e-2c53-4a1f-9083-8218ce0a7761 · inbound

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG cites this paper.

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:15:50.082045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 883c2d02-7a73-435e-96b7-daa1a9bd304a · inbound

Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models cites this paper.

Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:55:52.906909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4049c009-9922-4234-bd67-1e1ff8eebe64 · inbound

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing cites this paper.

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:32:52.107088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4b4b0dab-6a3f-4a77-a3dd-70cbd4b3efb0 · inbound

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure cites this paper.

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T08:23:29.666893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.